Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CULT+MATH Decision Briefs

REMOTE · CULTMATH.COM

Odds and forecasts on the numbers executives plan against, plus free studies and Decision Briefs.

Available components

+4 this week 79 Trust /100

Last scanned (17 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Education and Research

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability62
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 22906 tokens (~322/item across 71 items; 71 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
  • Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (83% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 71 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 72 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “list_standards” rewrote its description, which is the text the model reads security
    • New tool “get_framework” functional
    • New tool “list_frameworks” functional
  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “run_college_athletics” functional
    • New tool “run_sports_business_benchmark” functional
    • “run_concentration_benchmark” reworded the description of “peers” cosmetic
    • “run_disclosure_check” reworded the description of “peers” cosmetic
    • “run_peer_benchmark” reworded the description of “metric” cosmetic
  • 18 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “list_standards” rewrote its description, which is the text the model reads security
    • Tool “run_ai_visibility” rewrote its description, which is the text the model reads security
    • Tool “run_ai_visibility_quick” rewrote its description, which is the text the model reads security
    • Tool “run_angle_demand” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share_quick” rewrote its description, which is the text the model reads security
    • Tool “run_channel_mix” rewrote its description, which is the text the model reads security
    • Tool “run_city_profile” rewrote its description, which is the text the model reads security
    • Tool “run_claim_check” rewrote its description, which is the text the model reads security
    • Tool “run_comment_themes” rewrote its description, which is the text the model reads security
    • Tool “run_concentration_benchmark” rewrote its description, which is the text the model reads security
    • Tool “run_contractor_revenue” rewrote its description, which is the text the model reads security
    • Tool “run_cost_squeeze” rewrote its description, which is the text the model reads security
    • Tool “run_customer_concentration” rewrote its description, which is the text the model reads security
    • Tool “run_deal_activity” rewrote its description, which is the text the model reads security
    • Tool “run_deal_comps” rewrote its description, which is the text the model reads security
    • Tool “run_demand_check” rewrote its description, which is the text the model reads security
    • Tool “run_demand_durability” rewrote its description, which is the text the model reads security
    • Tool “run_disclosure_check” rewrote its description, which is the text the model reads security
    • Tool “run_effective_duty” rewrote its description, which is the text the model reads security
    • Tool “run_fad_check” rewrote its description, which is the text the model reads security
    • Tool “run_filing_trend” rewrote its description, which is the text the model reads security
    • Tool “run_launch_lift” rewrote its description, which is the text the model reads security
    • Tool “run_merger_review” rewrote its description, which is the text the model reads security
    • Tool “run_peer_benchmark” rewrote its description, which is the text the model reads security
    • Tool “run_premium_check” rewrote its description, which is the text the model reads security
    • Tool “run_private_raises” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_clock” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_trend” rewrote its description, which is the text the model reads security
    • Tool “run_revenue_mix” rewrote its description, which is the text the model reads security
    • Tool “run_series_forecast” rewrote its description, which is the text the model reads security
    • Tool “run_share_of_search” rewrote its description, which is the text the model reads security
    • Tool “run_spend_trend” rewrote its description, which is the text the model reads security
    • Tool “run_tariff_clock” rewrote its description, which is the text the model reads security
    • Tool “run_threshold_odds” rewrote its description, which is the text the model reads security
    • Tool “run_trade_concentration” rewrote its description, which is the text the model reads security
    • Tool “run_triangulation” rewrote its description, which is the text the model reads security
    • Tool “run_write_downs” rewrote its description, which is the text the model reads security
    • Schema quality: 285 → 324 ▼ functional
    • Tool coverage: 79% → 85% ▲ functional
    • New tool “run_ai_brand_check” functional
    • New tool “run_ai_readiness” functional
    • New tool “run_audience_map” functional
    • New tool “run_audience_size” functional
    • New tool “run_business_universe” functional
    • New tool “run_buyer_roles” functional
    • New tool “run_channel_benchmark” functional
    • New tool “run_device_clearances” functional
    • New tool “run_incentive_tracts” functional
    • New tool “run_news_pulse” functional
    • New tool “run_news_share_of_voice” functional
    • New tool “run_parcel_mix” functional
    • New tool “run_recall_watch” functional
    • New tool “run_search_vs_ai” functional
    • New tool “run_social_pulse” functional
    • New tool “run_social_share_of_voice” functional
    • New tool “run_topic_views” functional
    • New tool “run_trade_area” functional
    • New tool “run_trial_pipeline” functional
    • New tool “run_wallet_size” functional
  • 17 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “run_tariff_clock” rewrote its description, which is the text the model reads security
    • Schema quality: 10623 → 13405 ▼ functional
    • New tool “get_standard” functional
    • New tool “list_standards” functional
    • New tool “run_city_profile” functional
    • New tool “run_concentration_benchmark” functional
    • New tool “run_contractor_revenue” functional
    • New tool “run_deal_comps” functional
    • New tool “run_demand_durability” functional
    • New tool “run_merger_review” functional
    • New tool “run_private_raises” functional
    • New tool “tell_cultmath” functional
  • 16 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_decision_brief” rewrote its description, which is the text the model reads security
    • Tool “list_decisions” rewrote its description, which is the text the model reads security
    • Tool “run_trade_concentration” rewrote its description, which is the text the model reads security
    • New tool “run_effective_duty” functional
    • New tool “run_tariff_clock” functional
  • 15 Nov 26 +2
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_decision_brief” rewrote its description, which is the text the model reads security
    • Tool “get_document” rewrote its description, which is the text the model reads security
    • Tool “list_decision_briefs” rewrote its description, which is the text the model reads security
    • Tool “list_decisions” rewrote its description, which is the text the model reads security
    • Tool “run_ai_visibility” rewrote its description, which is the text the model reads security
    • Tool “run_ai_visibility_quick” rewrote its description, which is the text the model reads security
    • Tool “run_angle_demand” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share_quick” rewrote its description, which is the text the model reads security
    • Tool “run_channel_mix” rewrote its description, which is the text the model reads security
    • Tool “run_claim_check” rewrote its description, which is the text the model reads security
    • Tool “run_comment_themes” rewrote its description, which is the text the model reads security
    • Tool “run_cost_squeeze” rewrote its description, which is the text the model reads security
    • Tool “run_customer_concentration” rewrote its description, which is the text the model reads security
    • Tool “run_deal_activity” rewrote its description, which is the text the model reads security
    • Tool “run_demand_check” rewrote its description, which is the text the model reads security
    • Tool “run_disclosure_check” rewrote its description, which is the text the model reads security
    • Tool “run_fad_check” rewrote its description, which is the text the model reads security
    • Tool “run_filing_trend” rewrote its description, which is the text the model reads security
    • Tool “run_launch_lift” rewrote its description, which is the text the model reads security
    • Tool “run_peer_benchmark” rewrote its description, which is the text the model reads security
    • Tool “run_premium_check” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_clock” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_trend” rewrote its description, which is the text the model reads security
    • Tool “run_revenue_mix” rewrote its description, which is the text the model reads security
    • Tool “run_series_forecast” rewrote its description, which is the text the model reads security
    • Tool “run_share_of_search” rewrote its description, which is the text the model reads security
    • Tool “run_spend_trend” rewrote its description, which is the text the model reads security
    • Tool “run_threshold_odds” rewrote its description, which is the text the model reads security
    • Tool “run_trade_concentration” rewrote its description, which is the text the model reads security
    • Tool “run_triangulation” rewrote its description, which is the text the model reads security
    • Tool “run_write_downs” rewrote its description, which is the text the model reads security
    • Tool “search_cultmath” rewrote its description, which is the text the model reads security
    • Schema quality: 325 → 281 ▲ functional
    • Tool “run_ai_visibility” now declares an output schema ▲ functional
    • Tool “run_ai_visibility_quick” now declares an output schema ▲ functional
    • Tool “run_angle_demand” now declares an output schema ▲ functional
    • Tool “run_answer_share” now declares an output schema ▲ functional
    • Tool “run_answer_share_quick” now declares an output schema ▲ functional
    • Tool “run_channel_mix” now declares an output schema ▲ functional
    • Tool “run_claim_check” now declares an output schema ▲ functional
    • Tool “run_comment_themes” now declares an output schema ▲ functional
    • Tool “run_cost_squeeze” now declares an output schema ▲ functional
    • Tool “run_customer_concentration” now declares an output schema ▲ functional
    • Tool “run_deal_activity” now declares an output schema ▲ functional
    • Tool “run_demand_check” now declares an output schema ▲ functional
    • Tool “run_disclosure_check” now declares an output schema ▲ functional
    • Tool “run_fad_check” now declares an output schema ▲ functional
    • Tool “run_filing_trend” now declares an output schema ▲ functional
    • Tool “run_launch_lift” now declares an output schema ▲ functional
    • Tool “run_peer_benchmark” now declares an output schema ▲ functional
    • Tool “run_premium_check” now declares an output schema ▲ functional
    • Tool “run_regulatory_clock” now declares an output schema ▲ functional
    • Tool “run_regulatory_trend” now declares an output schema ▲ functional
    • Tool “run_revenue_mix” now declares an output schema ▲ functional
    • Tool “run_series_forecast” now declares an output schema ▲ functional
    • Tool “run_share_of_search” now declares an output schema ▲ functional
    • Tool “run_spend_trend” now declares an output schema ▲ functional
    • Tool “run_threshold_odds” now declares an output schema ▲ functional
    • Tool “run_trade_concentration” now declares an output schema ▲ functional
    • Tool “run_triangulation” now declares an output schema ▲ functional
    • Tool “run_write_downs” now declares an output schema ▲ functional
    • First check of Tool coverage: 80 functional
    • “get_decision_evidence” reworded the description of “decision_id” cosmetic
    • “run_premium_check” reworded the description of “brand” cosmetic
  • 14 Nov 26 0
    • Server version: 1.2.0 → 1.3.0 functional
    • New tool “run_series_forecast” functional
    • New tool “run_threshold_odds” functional
  • 13 Nov 26 +1
    • Tool “run_ai_visibility” rewrote its description, which is the text the model reads security
    • Tool “run_ai_visibility_quick” rewrote its description, which is the text the model reads security
    • Tool “run_angle_demand” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share” rewrote its description, which is the text the model reads security
    • Tool “run_answer_share_quick” rewrote its description, which is the text the model reads security
    • Tool “run_channel_mix” rewrote its description, which is the text the model reads security
    • Tool “run_claim_check” rewrote its description, which is the text the model reads security
    • Tool “run_deal_activity” rewrote its description, which is the text the model reads security
    • Tool “run_demand_check” rewrote its description, which is the text the model reads security
    • Tool “run_disclosure_check” rewrote its description, which is the text the model reads security
    • Tool “run_fad_check” rewrote its description, which is the text the model reads security
    • Tool “run_filing_trend” rewrote its description, which is the text the model reads security
    • Tool “run_peer_benchmark” rewrote its description, which is the text the model reads security
    • Tool “run_premium_check” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_clock” rewrote its description, which is the text the model reads security
    • Tool “run_regulatory_trend” rewrote its description, which is the text the model reads security
    • Tool “run_share_of_search” rewrote its description, which is the text the model reads security
    • Tool “run_spend_trend” rewrote its description, which is the text the model reads security
    • Tool “run_triangulation” rewrote its description, which is the text the model reads security
    • Schema quality: 8000 → 10525 ▼ functional
    • New tool “run_comment_themes” functional
    • New tool “run_cost_squeeze” functional
    • New tool “run_customer_concentration” functional
    • New tool “run_launch_lift” functional
    • New tool “run_revenue_mix” functional
    • New tool “run_trade_concentration” functional
    • New tool “run_write_downs” functional
    • “run_peer_benchmark” reworded the description of “metric” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://cultmath.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=cultmath.com CN=YR1,O=Let's Encrypt,C=US 17 Oct 2026 15 Jan 2027 RSA 2048 SHA256-RSA 64b6c7c8768c332cb6dfd69acad993cff7e
SANs: cultmath.com
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of cultmath.com. — Secure

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
cultmath.com. DS published 2371 13 Verified
cultmath.com. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy default-src 'self'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src https://fonts.gstatic.com; img-src 'self' data: https://www.googletagmanager.com https://*.google.com https://*.googleadservices.com https://*.doubleclick.net https://px.ads.linkedin.com https://i.ytimg.com; script-src 'self' 'unsafe-inline' https://www.googletagmanager.com https://www.googleadservices.com https://www.google.com https://snap.licdn.com; frame-src 'self' https://shaman.cultmath.com https://td.doubleclick.net https://www.googletagmanager.com https://www.youtube-nocookie.com; connect-src 'self' https://www.googletagmanager.com https://*.google-analytics.com https://*.analytics.google.com https://*.google.com https://*.googleadservices.com https://*.doubleclick.net https://px.ads.linkedin.com
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://cultmath.com/mcp Verified 200
http (plaintext) http://cultmath.com/mcp HTTPS enforced 308 https://cultmath.com/mcp
MCP tools · 71 exposed · ~22,358 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
buy_decision_evidence ~113

Starts a Stripe checkout for the full evidence behind one decision: sourced and dated figures, what would flip the answer, and the brief's stated limits. Returns a checkout URL for the user to approve and pay, and a session_id. After the user pays, call get_decision_evidence with both ids. Always show the price and get the user's go-ahead before sending them to pay.

NameTypeReqDescription
decision_idstringyesFrom list_decisions, e.g. "cpg-premium/02".

No output schema declared.

No examples provided.

get_decision_brief ~107

Everything public about one brief: the decisions it covers (six or more) with the evidence line for each, pages, edition, price, sample pages, free answers, guarantee, license and payment link. The PDF itself is delivered only after payment. To buy one decision instead of the whole brief, use list_decisions, then buy_decision_evidence.

NameTypeReqDescription
idstringyesBrief id from list_decision_briefs, e.g. "cpg-premium".

No output schema declared.

No examples provided.

get_decision_evidence ~112

Returns the full evidence for one decision once it is paid for. Pass the session_id from buy_decision_evidence, or the Checkout Session id of a full brief, team license, pack or all-access purchase that includes this decision.

NameTypeReqDescription
decision_idstringyesThe id from list_decisions, e.g. "cpg-premium/02": the same id passed to buy_decision_evidence.
session_idstringyesA Stripe Checkout Session id (cs_live_...).

No output schema declared.

No examples provided.

get_document ~97

Read every published finding (question and answer) of one CULT+MATH study or answer page, with its date, license, citation line and related brief. Use it on a URL that search_cultmath returned; for a paid brief's outline, use get_decision_brief instead.

NameTypeReqDescription
urlstringyesA cultmath.com/research/... or /answers/... URL from search_cultmath, or its last path segment.

No output schema declared.

No examples provided.

get_framework ~110

Free. Returns one framework in full: its rule, its trap, its text, the run_* tools that put sourced numbers behind each step (with the question each answers), a real published case with its date, and where it is used. Use it to apply the framework to the user's situation step by step.

NameTypeReqDescription
slugstringyesThe framework's slug or name, e.g. "the-monocrop", "monocrop", "signal-noise-split". From list_frameworks.

No output schema declared.

No examples provided.

get_standard ~128

Free. Returns the full text of one DEOS Open standard (when to use it, the rules, how to run it, done when, common failures, template), with its link, version and license, and the JSON Schema link for the four that have one (C1, C3, C5, C13). Use it to follow a standard exactly rather than from memory.

NameTypeReqDescription
idstringyesThe standard's id, e.g. "C1" (Decision Record), "C13" (Six-Lens Board), "R3" (Category Entry Point Read).

No output schema declared.

No examples provided.

list_decision_briefs ~99

List the CULT+MATH Decision Briefs: who each is written for, its headline finding, price, page and payment link. Also lists bundles and the custom brief. To read one brief in full, use get_decision_brief; to buy a single decision rather than a whole brief, use list_decisions.

NameTypeReqDescription
categorystring–Optional filter, e.g. "CPG", "Entertainment", "Private equity".

No output schema declared.

No examples provided.

list_decisions ~102

The single decisions inside the briefs (six or more per brief), each with who owns it, who contests it, and the public evidence line. Use an id with buy_decision_evidence to buy the full evidence for just that decision. For whole briefs, use list_decision_briefs.

NameTypeReqDescription
brief_idstring–Optional: only this brief, e.g. "cpg-premium".
querystring–Optional keywords to filter by.

No output schema declared.

No examples provided.

list_frameworks ~61

Free. Lists the CULT+MATH frameworks: short, named ways to read a decision (customer concentration, line extensions, positioning, signal versus noise, a business at its turn), each with the runs that supply its evidence. Read one with get_framework.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_standards ~112

Free. Lists every DEOS Open working standard (decisions, research, marketing, product, projects): each one's id, title, module and one-line rule, with its link. Use it to find the standard that fits a task, then read it with get_standard. DEOS Open is CC BY 4.0; credit "DEOS Open, Ipalibo Da-Wariboko, CULT+MATH LLC".

NameTypeReqDescription
modulestring–Optional: only the standards in one module.

No output schema declared.

No examples provided.

run_ai_brand_check ~325

Use when the user asks what ChatGPT, Claude, Gemini or Perplexity say about their company, or whether assistants get their facts right: "does ChatGPT know where we are based?", "do AI assistants know our pricing?". Asks four assistants about the brand twice each and returns how many answers recognize it, how many state each fact you give, and a short excerpt where each appears. An answer that leaves a fact out is not marked wrong. Refuses before you are charged if too few answers come back or your values are too generic to test. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run to build a series; segment: facts (each fact checked). Price: $0.83 per run over x402 (USDC on Base, no account needed), or $1.15 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For whether the brand’s site is cited, rather than described, use run_ai_visibility.

NameTypeReqDescription
brandstringyesThe brand as buyers say it.
factsobjectyesLabel and value pairs, e.g. {"headquarters":"Houston","founded":"2019"}.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_ai_readiness ~314

Use when the user asks why AI assistants do not cite their site, whether their site is "AI friendly", or whether they block ChatGPT, Claude or Perplexity: "is our robots.txt blocking AI?", "do we need an llms.txt?". Reads the site’s robots.txt (verdicts for 11 AI crawler tokens, grouped into search, live fetch and training), its llms.txt and its home page without running scripts (readability, H1, schema.org types, meta description, noindex), and returns a pass/fail checklist with a plain fix for each failure. Refuses before you are charged if the site cannot be read. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run after a fix. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For whether AI answers cite the site for a buyer question, use run_ai_visibility.

NameTypeReqDescription
domainstringyesA public domain name, e.g. "example.com".
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_ai_visibility ~442

Use when the user asks whether their brand or website shows up in AI answers, or who AI assistants cite instead. Asks ChatGPT, Claude, Gemini and Perplexity the buyer's question live with web search on, three times each on the everyday model and once on the flagship model, and returns per platform: in how many askings the domain was cited and at what positions, whether that held every time, and whether the flagship model agrees. Also how many platforms cite it and the domains cited most instead (not the answers themselves). A platform that cites nothing is reported as not measured. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run to build a series; segment: question (one buyer question per run). Price: $1.47 per run over x402 (USDC on Base, no account needed), or $1.80 over MPP (a Stripe shared payment token). Fixed price per run, not per answer. Charged in full when at least 3 of 4 platforms are measured (a platform counts when at least 2 of its 3 askings answer with sources); otherwise it refuses and nothing is charged. So a charged run can rest on fewer than all 16 answers; the result reports exactly how many, per platform. For a cheaper read without the flagship-model check, use run_ai_visibility_quick; for who owns a category's answers rather than one domain, use run_answer_share. A real sample of this run, free: https://cultmath.com/agent/samples/ai-visibility.json

NameTypeReqDescription
domainstringyesThe domain to look for, e.g. example.com. Its subdomains count.
questionstringyesThe question a buyer would ask an AI assistant. No personal data.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_ai_visibility_quick ~390

Use when the user asks whether their brand or website shows up in AI answers and a quick read is enough. Asks ChatGPT, Claude, Gemini and Perplexity the buyer's question live with web search on, twice each on the everyday model, and returns per platform: in how many askings the domain was cited and at what positions and whether that held both times, plus the domains cited most instead (not the answers themselves). No flagship-model comparison; that is run_ai_visibility. Buy more runs to cover more questions. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run to build a series; segment: question. Price: $0.74 per run over x402 (USDC on Base, no account needed), or $1.06 over MPP (a Stripe shared payment token). Fixed price per run, not per answer. Charged in full when at least 3 of 4 platforms are measured (a platform counts when both of its 2 askings answer with sources); otherwise it refuses and nothing is charged. So a charged run can rest on fewer than all 8 answers; the result reports exactly how many, per platform. A real sample of this run, free: https://cultmath.com/agent/samples/ai-visibility-quick.json

NameTypeReqDescription
domainstringyesThe domain to look for, e.g. example.com. Its subdomains count.
questionstringyesThe question a buyer would ask an AI assistant. No personal data.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_angle_demand ~331

Use when the user is choosing a positioning, a message or a campaign angle and asks which benefit or reason to buy matters most to buyers, or which is gaining. Returns, for each angle searched with the category, its share of searches among the angles named, its year-on-year change and its growth beyond an everyday control basket, with a volume band. Shares and bands only. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: share and growth over 12 months; segment: angles (each buying reason). Price: $0.07 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For brands' shares of search, use run_share_of_search; for whether competitors already claim an angle, use run_claim_check. A real sample of this run, free: https://cultmath.com/agent/samples/angle-demand.json

NameTypeReqDescription
anglesstringyes2-6 reasons to buy, comma-separated, e.g. "healthy,vegan,keto,cheap".
categorystringyesThe category as people search for it, e.g. "protein snacks".
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_answer_share ~445

Use when the user asks which brands or websites AI assistants rely on for their category, who they are competing with in AI answers, or whether any source dominates. Asks ChatGPT, Claude, Gemini and Perplexity 2-3 buyer questions live, each twice, and returns the most-cited domains as counts of answers, whether the category is owned, led, contested or fragmented, whether the leaders hold from one asking to the next, and, if given, where your domain stands. Not the answers themselves. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run to build a series; segment: q1-q3 (buyer questions). Price: $2.20 per run over x402 (USDC on Base, no account needed), or $2.54 over MPP (a Stripe shared payment token). Fixed price per run, not per answer. Charged in full when at least half the answers cite sources and at least 3 of 4 platforms do; otherwise it refuses and nothing is charged. So a charged run can rest on as few as 12 of 24 answers (fewer with two questions); the result reports exactly how many (controls.measurement). For a cheaper single pass, use run_answer_share_quick; for whether one domain is cited, use run_ai_visibility. A real sample of this run, free: https://cultmath.com/agent/samples/answer-share.json

NameTypeReqDescription
domainstring–Optional: your domain, e.g. example.com, to see where it stands.
q1stringyesA question a buyer in the category would ask an AI assistant. No personal data.
q2stringyesA second, different buyer question.
q3string–Optional third question.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_answer_share_quick ~403

Use when the user asks which brands or websites AI assistants rely on for their category and a quick read is enough. Asks ChatGPT, Claude, Gemini and Perplexity two buyer questions live, once each, and returns the most-cited domains as counts of answers, whether the category is owned, led, contested or fragmented, and, if given, where your domain stands. Not the answers themselves. No stability check; buy a second run, or use run_answer_share, to see whether the leaders hold. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; re-run to build a series; segment: q1-q2. Price: $0.74 per run over x402 (USDC on Base, no account needed), or $1.06 over MPP (a Stripe shared payment token). Fixed price per run, not per answer. Charged in full when at least half the answers cite sources and at least 3 of 4 platforms do; otherwise it refuses and nothing is charged. So a charged run can rest on as few as 4 of 8 answers; the result reports exactly how many (controls.measurement). A real sample of this run, free: https://cultmath.com/agent/samples/answer-share-quick.json

NameTypeReqDescription
domainstring–Optional: your domain, e.g. example.com, to see where it stands.
q1stringyesA question a buyer in the category would ask an AI assistant. No personal data.
q2stringyesA second, different buyer question.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_audience_map ~439

Use when the user is choosing where to target, open, or send sales or media: "which Texas counties have the most high-income young households?", "which Harris County tracts concentrate households 65 and over?". Ranks the counties of a state, or the tracts of a county, by the number and the concentration of households with a householder in the chosen age bands and income range, from ACS 5-year estimates, with margins of error. Refuses before you are charged if the table does not reconcile. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one release (ACS 2020-2024); place: state (counties) or county (tracts); segment: age_bands, income_min-income_max. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For the audience count with a margin of error, use run_audience_size.

NameTypeReqDescription
age_bandsarray–Householder age bands. Default all four.
countystring–Optional three-digit county FIPS code: ranks its tracts instead of the state’s counties.
income_maxinteger–Optional household income ceiling, at the same edges.
income_mininteger–Household income floor, one of 0, 10000, 15000, 20000, 25000, 30000, 35000, 40000, 45000, 50000, 60000, 75000, 100000, 125000, 150000, 200000.
statestringyesTwo-letter US state code.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_audience_size ~523

Use when the user is defining or sizing a consumer audience or checking a TAM claim: "how many college-educated 25-34 year olds are in the US?", "how many homeowner households in Texas earn over $150,000?". Counts people or households matching a profile from the 2024 ACS microdata, with a 90% margin of error and the share of the area. No filters on race, ethnicity, religion or disability. Refuses before you are charged if the weights do not reproduce the published population or the sample is too thin. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one release (ACS 2024); place: state or pumas; segment: age, sex, income, education, employed, tenure, children, occupations. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For where that audience lives, use run_audience_map; for what it spends, use run_wallet_size.

NameTypeReqDescription
age_maxinteger–Oldest age, in years.
age_mininteger–Youngest age, in years.
childrenboolean–true: children at home; false: none.
educationstring–Minimum education.
employedboolean–true to count only the employed.
household_income_maxinteger–Household income ceiling, dollars a year.
household_income_mininteger–Household income floor, dollars a year.
occupationsarray–Census occupation codes (OCCP), up to 5.
personal_income_maxinteger–Personal income ceiling, dollars a year.
personal_income_mininteger–Personal income floor, dollars a year.
pumasarray–Optional: up to 10 PUMA codes within the state.
sexstring–Optional: one sex.
statestring–Two-letter US state code, or US.
tenurestring–Owner or renter households.
unitstring–Count people or households. Default persons.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_business_universe ~383

Use when the user is sizing a B2B market in firms, planning a roll-up or territory, or asks how many companies of a kind exist: "how many CPA firms are in Texas?", "how many restaurants are in Harris County, and how big are they?". Returns employer establishments, employees and payroll from County Business Patterns, the split by employee size, and solo businesses with no payroll from Nonemployer Statistics. Refuses before you are charged if the code matches nothing or the size classes do not add up. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one release (latest County Business Patterns and Nonemployer year); place: state, county, cbsa or zip; segment: naics; size class (in the result). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For how many people hold the buyer’s job in the area, use run_buyer_roles.

NameTypeReqDescription
cbsastring–Five-digit metro area code, e.g. 26420 for Houston.
countystring–Three-digit county FIPS code, with state.
naicsstringyesNAICS industry code, 2-6 digits.
statestring–Two-letter US state code, or US.
zipstring–Five-digit ZIP code (employer data only).
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_buyer_roles ~328

Use when the user is sizing a B2B buyer persona or a hiring market: "how many marketing managers are in Houston?", "how many accountants work in Texas and what do they earn?". Returns employment, mean and median annual wage, jobs per 1,000, and the location quotient against the nation, from BLS OEWS. Wage-and-salary jobs only. Refuses before you are charged if BLS suppresses the estimate or the series do not line up. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one release (latest May OEWS); place: state or cbsa; segment: soc (occupation). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For how many businesses employ them, use run_business_universe.

NameTypeReqDescription
cbsastring–Five-digit metro area code, e.g. 26420 for Houston.
socstringyesSix-digit SOC occupation code, e.g. 11-2021 (marketing managers).
statestring–Two-letter US state code, or US.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_channel_benchmark ~361

Use when the user is a creator or brand-partnership lead comparing channels: "how does my channel stack up against these three?", "who posts more Shorts and does it pay?", "which creator should we sponsor?". Returns, for each channel over the window, uploads per week, share of Shorts, median views for long-form and Shorts, median views per day, likes and comments per 1,000 views, and optionally how titles with your words perform. Public counts only; results cannot be published. Refuses before you are charged if a channel does not resolve. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one window of days; compare: channels (2-5); segment: format (Shorts, long-form); terms. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For which topics on a subject get views across all channels, use run_topic_views.

NameTypeReqDescription
channelsarrayyes2-5 channels, each an @handle (e.g. "@mkbhd") or a channel id starting UC.
daysinteger–Days back from today. Default 90.
termsarray–Optional: up to 4 title words to compare titles with and without them.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_channel_mix ~412

Use when the user is planning go-to-market or channel strategy and asks where buyers look, whether to prioritise retail, review sites, their own site or communities, or who controls the first page for their category. Searches Google live for 1-3 buyer queries and classes every top-10 organic result by domain: retailers and marketplaces, reviews and media, brand sites, forums and social, reference, independent and specialist sites. Returns the share each class holds, who leads each class, and who takes the top three places. Domains and counts only. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; compare: brand_domains, retailer_domains, media_domains; segment: q1-q3 (buyer searches). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For each brand's share of searches, use run_share_of_search. A real sample of this run, free: https://cultmath.com/agent/samples/channel-mix.json

NameTypeReqDescription
brand_domainsstring–Optional: the category's brand sites, comma-separated, so they are classed as brands.
media_domainsstring–Optional: specialist review or media sites to class as media.
q1stringyesA search a buyer would make, e.g. "best protein bars".
q2string–Optional second search.
q3string–Optional third search.
retailer_domainsstring–Optional: specialist retailers to class as retailers.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_city_profile ~418

Use when the user is weighing a housing, zoning, development or site decision for a US city, or checking a claim about one: "is Boise building enough housing?", "how fast has rent risen in St. Paul against the country?", "did permits in Austin fall after 2022?". Returns population, households, median rent, median income, rent burden and work-from-home share in 2019 and 2023-2025 beside the US, and new housing units permitted each year from 2015 to 2025 (all and in 5+ unit buildings), per 1,000 residents, from US Census Bureau data. Cities of 65,000+ residents that file their own permits. Refuses before you are charged if the city cannot be matched, its permits are filed by another office, or its permit file is not believable (a large city reporting no apartment permits, or far below its county). Describes; takes no side on any policy. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: 2019 against 2023-2025, permits 2015-2025; place: state and place. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound.

NameTypeReqDescription
placestringyesThe city name as people write it, e.g. "St. Paul" or "Nashville". Cities of 65,000+ residents.
statestringyesTwo-letter US state code, e.g. "MN". DC included.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_claim_check ~364

Use when the user is choosing a positioning, a tagline or a message and asks whether competitors already say it, whether a claim is crowded or open, or who has moved onto it recently. Reads each competitor's home page today and its Internet Archive copy from a year ago, and returns, per site, whether it leads with the claim, mentions it, or does not, and whether that changed this year, with a verdict: open, mentioned but not owned, taken, or crowded. No page text is returned. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: today against a year ago; compare: sites (3-5 competitors); segment: variants (wordings of the claim). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For whether people search for that reason to buy, use run_angle_demand. A real sample of this run, free: https://cultmath.com/agent/samples/claim-check.json

NameTypeReqDescription
claimstringyesThe claim as a buyer would read it, e.g. "plant-based protein".
sitesstringyes3-5 competitor domains, comma-separated.
variantsstring–Optional: up to 3 other wordings, comma-separated.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_college_athletics ~445

Use when the user is an athletic director, conference or university finance staff, or a sponsor, apparel or media partner sizing a college program: "how much does Texas athletics bring in?", "how dependent is this school on football?", "where does our program rank in the Big Ten?". Returns one NCAA Division I school's reported athletics revenue and expenses for 2024-25, split by football, men's and women's basketball, other men's and women's sports and not allocated; football and men's basketball as a share of revenue allocated to sports; athletes per sport; and its rank and the median in its Division I classification or in the schools you name. EADA has no conference field, so for a conference, name its members. Refuses before you are charged if the school is not an exact match, and lists candidates. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one EADA data year; compare: compare (2-20 schools) or the school's Division I classification; segment: sport; men and women (in the result). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For listed sports companies rather than schools, use run_sports_business_benchmark.

NameTypeReqDescription
comparearray–Optional: 2-20 schools to compare with, e.g. a conference's members, by name or UNITID. Leave out to compare with the school's own classification (FBS, FCS or Division I without football).
schoolstringyesA Division I school's name as IPEDS lists it (e.g. "University of Texas at Austin") or its 6-digit UNITID (e.g. "228778").
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_comment_themes ~293

Use when the user wants to know what viewers raise under a trailer, launch video, ad or review on YouTube, for example whether they talk about price, a feature or a complaint. Returns, for up to eight themes named in advance, the count and share of up to 400 top comments per video (up to five videos) that mention each, with how many comments were read. No comment text. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one moment; compare: videos (up to five); segment: themes. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound.

NameTypeReqDescription
themesstringyes1-8 words or short phrases to count, comma-separated, e.g. "disc,price,story".
videosstringyes1-5 YouTube video IDs (the 11 characters after v= in the link), comma-separated.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_concentration_benchmark ~479

Use when the user is pricing customer-concentration risk in a deal or asks whether a target’s reliance on one customer (often Walmart) is unusual: "our target gets 32% from Walmart, is that high for food companies?". Returns each peer’s largest-customer share of revenue from its latest 10-K XBRL, the peer median and range, and where the target sits. Peers that tag no figure are listed as unknown, never zero. Refuses before you are charged if fewer than two peers can be measured. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: one release (latest 10-Ks); compare: peers. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For one company’s largest customer over three years, use run_customer_concentration.

NameTypeReqDescription
peersstringyes2-6 peer tickers, comma-separated, from: PEP, KO, K, POST, KDP, CELH, UTZ, HRL, GIS, KHC, CAG, CPB, HSY, MDLZ, SJM, CLX, CL, CHD, PG, SMPL, BRBR, MSFT, EA, TTWO, RBLX, OMC, STGW, CRM, HUBS, TDOC, TAL…
target_sharenumber–Optional: a private target’s largest customer as a percent of revenue, from its own books. Not with ticker.
tickerstring–Optional: a public company from the same list to place against the peers. Not with target_share.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_contractor_revenue ~314

Use when the user is diligencing a government-services or defense target, sizing recompete risk, or asks how dependent a company is on one agency: "how much does this contractor get from the Army?", "is their federal revenue concentrated?". Returns prime contract obligations by federal fiscal year, the top awarding agencies with their shares, an agency concentration index (HHI) and the recipient names matched, from USAspending.gov. Obligations, not revenue. Refuses before you are charged if nothing is found or the totals do not reconcile. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: by fiscal year (years); segment: awarding agency (in the result). Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For federal spending across a whole topic, use run_spend_trend.

NameTypeReqDescription
recipientstringyesThe company as it appears on federal awards.
yearsinteger–Fiscal years to cover, ending with the current one. Default 5.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_cost_squeeze ~290

Use when the user asks whether a commodity shock (cocoa, coffee, sugar, wheat, corn, beef, aluminum, crude oil) has squeezed a public company's margin, whether it passed the cost through, or what a price spike will do to a supplier. Returns the commodity's average price change and the company's gross margin for each fiscal year since 2019, with a verdict: squeezed, held, or widened. Refuses before you are charged if the commodity moved less than 25%. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: fiscal years since 2019; segment: commodity. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For where US imports of a product come from, use run_trade_concentration.

NameTypeReqDescription
commoditystringyesThe input, as an IMF global price.
tickerstringyesThe company.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_customer_concentration ~249

Use when the user asks how much of a public company's revenue comes from one retailer or customer (for example Walmart), or is weighing the risk of selling through a dominant buyer. Returns the largest customer's share of revenue for each fiscal year tagged in the company's three latest 10-Ks, the customer's name as tagged, and each filing's citation. Refuses before you are charged if no share is tagged. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: three latest 10-Ks. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For revenue by segment or region, use run_revenue_mix.

NameTypeReqDescription
tickerstringyesThe company.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_deal_activity ~419

Use when the user asks about M&A activity, deal flow or consolidation in a sector, whether now is a good time to buy or sell a company in it, or who the active acquirers are. Returns, quarter by quarter, the 8-K merger-agreement documents that mention the sector as a share of all 8-K merger agreements, from SEC EDGAR full-text search, whether that share is rising or falling, an industry-code cross-check, and the most active filers with their latest filing linked. It counts documents, not deals, and gives no deal values or multiples. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: share by quarter (quarters); segment: sector, phrase or SIC code. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For one company's write-downs of what it bought, use run_write_downs. A real sample of this run, free: https://cultmath.com/agent/samples/deal-activity.json

NameTypeReqDescription
phrasestring–Your own sector phrase, without quote marks, if no named sector fits. Not with sector.
quartersinteger–How many quarters, ending with the last complete one. Default 8.
sectorstring–A named sector, with its phrase and industry codes set for you. Or give phrase instead.
sicstring–Optional, with phrase: four-digit SIC codes for the cross-check, comma-separated, e.g. "7372,7373".
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_deal_comps ~352

Use when the user is underwriting an entry or exit multiple, pricing an acquisition, or asks what similar companies sold for: "what EBITDA multiples are cybersecurity deals getting?", "what did bankers use as comps for CPG deals?". Reads the most recent merger proxies (DEFM14A) and S-4s that mention a precedent-transactions analysis and the sector, and returns every EV/EBITDA and EV/revenue range the advisors applied, the sentence it came from and a link to the filing. These are the advisors’ chosen comparables, not market prices, and are never averaged. Refuses before you are charged if no range can be read. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: proxies over the last years; segment: sector or phrase. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For whether deal activity in the sector is rising, use run_deal_activity.

NameTypeReqDescription
phrasestring–Your own sector phrase, without quote marks. Not with sector.
sectorstring–A named sector. Or give phrase instead.
yearsinteger–How many years back to search. Default 3.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_demand_check ~346

Use when the user asks whether interest in a product, category or trend is really growing, or wants to know if a rise in search is more than noise before investing in it. Returns the category's year-on-year search change against an everyday basket of ten unrelated searches (its growth beyond the market), a volume band, and whether SEC 10-K filings confirm the direction, the costly-to-fake check. Changes and bands only, never monthly volumes. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: latest 12 months against the 12 before; segment: also (a second phrase for the category). Price: $0.07 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For whether interest is lasting or past its peak, use run_fad_check; for brands' shares of search, use run_share_of_search. A real sample of this run, free: https://cultmath.com/agent/samples/demand-check.json

NameTypeReqDescription
alsostring–Optional: up to 4 more keywords for the same category, comma-separated.
phrasestringyesThe category as people search for it, e.g. "protein snacks".
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_demand_durability ~330

Use when the user is checking a consumer target’s growth story in diligence, or asks whether a brand’s momentum will last: "is Celsius still gaining on Monster?", "is this brand a fad?". Runs share-of-search against the rivals you name and fad-check on the brand, and returns both readings with a combined label: durable, at risk, or mixed when they disagree. Each part keeps its own controls; if either refuses, nothing is charged. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: 12 months against the 12 before, and since 2016; compare: rivals. Price: $0.11 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For share of search alone, use run_share_of_search; for the fad reading alone, use run_fad_check.

NameTypeReqDescription
articlestringyesThe English Wikipedia article on the brand or its company, e.g. "Celsius Holdings".
brandstringyesThe brand as people search for it.
rivalsstringyes2-6 competing brands, comma-separated.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

run_device_clearances ~337

Use when the user is sizing competition in a medical device category, diligencing a medtech target, or asks who is bringing devices to market: "how many pulse oximeters got 510(k) clearance?", "which companies are clearing devices under product code DQA?". Returns FDA 510(k) decisions per year from openFDA, whether they are rising or falling, and the most active applicants. Clearances, not sales. Refuses before you are charged if the category matches nothing. Every result carries a run id, a date and a citation line. Calling this tool returns a quote, not the result: what the run measures, its price and a payment_url. The run happens only when you POST to payment_url, and a run that fails its controls refuses there with nothing charged. Dimensions (vary these inputs to cut the answer; each call is its own run): over time: built in: by year (years); segment: product_code or device. Price: $0.05 per run over x402 (USDC on Base, no account needed), or $0.50 over MPP (a Stripe shared payment token); charged only when the run comes back sound. For recalls in the category, use run_recall_watch.

NameTypeReqDescription
devicestring–A device phrase matched against device names, e.g. "pulse oximeter". Give this or product_code.
product_codestring–The FDA three-letter product code, e.g. "DQA". Give this or device.
yearsinteger–Complete calendar years to cover, ending last year. Default 6.
NameTypeReqDescription
availableboolean–false when the run is switched off; then nothing can be charged.
errorstring–Why the inputs were refused, with the expected usage. Nothing is charged.
instructionsobject–How to pay over MPP and x402, and how to ask for publication.
limits––What the run cannot tell you, stated before you pay.
next_stepstring–What to tell the user before paying.
notestring–Why the run is unavailable, when it is.
payment_urlstring–POST here to run and pay. Not a checkout page.
price_usdnumber–Price over MPP (Stripe shared payment token).
recipestring–The run, e.g. "filing-trend".
what_you_getstring–What the paid result will contain for these inputs.
x402_price_usdnumber–Price over x402 (USDC on Base), when offered.

No examples provided.

Install

How do I install the CULT+MATH Decision Briefs MCP server?

CULT+MATH Decision Briefs is a hosted endpoint at https://cultmath.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · cultmath.com

# add to Claude Code
claude mcp add --transport http com-cultmath-decision-briefs 'https://cultmath.com/mcp'
Common questions

What is the CULT+MATH Decision Briefs MCP server?

CULT+MATH Decision Briefs is an MCP server listed in the public MCP registry as com.cultmath/decision-briefs. Odds and forecasts on the numbers executives plan against, plus free studies and Decision Briefs. This page covers its hosted endpoint (https://cultmath.com/mcp).

Is the CULT+MATH Decision Briefs MCP server safe to use?

CULT+MATH Decision Briefs scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CULT+MATH Decision Briefs MCP server expose?

CULT+MATH Decision Briefs exposes 71 tools: list_decision_briefs, get_decision_brief, search_cultmath, list_decisions, buy_decision_evidence, and 66 more. Their descriptions and schemas cost roughly 22,358 tokens of context every time the server is loaded.

Does the CULT+MATH Decision Briefs MCP server require authentication?

No. We connected to CULT+MATH Decision Briefs without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the CULT+MATH Decision Briefs MCP server still maintained?

CULT+MATH Decision Briefs is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the CULT+MATH Decision Briefs MCP server?

VerifyMCP ran 13 checks on CULT+MATH Decision Briefs, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.