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.

Agent Weather

REMOTE · MCP.AGENTWEATHER.IO

Open-source intelligence for AI agents: public readings, each with its source and timestamp.

72 Trust /100

Last scanned (10 hours ago)

Scores higher than 63% of remote servers

Reachable. Last reached 18 Oct 2026.

Category AI and Machine Learning

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 Security74
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 4541 tokens (~216/item across 21 items; 21 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 Management20
  • Stability observed for 6 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 21 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 22 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
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.

  • 17 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “decide_cheapest_model” rewrote its description, which is the text the model reads security
    • Tool “decide_provider_health” rewrote its description, which is the text the model reads security
    • Tool “get_current_conditions” rewrote its description, which is the text the model reads security
    • Tool “get_merchant_profile” rewrote its description, which is the text the model reads security
    • Tool “get_merchant_readings” rewrote its description, which is the text the model reads security
    • Tool “get_x402_activity” rewrote its description, which is the text the model reads security
    • Tool “decide_provider_health” changed its title: Pre-flight: AI provider conditions (paid: 0.001 RLUSD or 0.001 USDC on Base via x402) → AI provider health reading (paid: 0.005 RLUSD or 0.005 USDC on Base via x402) cosmetic
    • Tool “get_current_conditions” changed its title: Current conditions report (paid: 0.01 RLUSD or 0.01 USDC on Base via x402) → Combined record: AI provider health, x402 on XRPL, agent tooling (paid: 0.007 RLUSD or 0.007 USDC on Base via x402) cosmetic
    • Tool “get_merchant_profile” changed its title: x402 merchant readings (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) (alias of get_merchant_readings) → x402 merchant readings (paid: 0.02 RLUSD or 0.02 USDC on Base via x402) (alias of get_merchant_readings) cosmetic
    • Tool “get_merchant_readings” changed its title: x402 merchant readings (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) → x402 merchant readings (paid: 0.02 RLUSD or 0.02 USDC on Base via x402) cosmetic
  • 16 Oct 26 +4
    • HTTPS: unverified → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “decide_cheapest_model” rewrote its description, which is the text the model reads security
    • Tool “decide_provider_health” rewrote its description, which is the text the model reads security
    • Tool “get_price_index” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_facilitator” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_providers” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_storm” rewrote its description, which is the text the model reads security
    • Tool “get_x402_activity” rewrote its description, which is the text the model reads security
    • Tool “paycheck” rewrote its description, which is the text the model reads security
    • Tool “payradar” rewrote its description, which is the text the model reads security
    • Server version: 0.4.2 → 0.4.3 functional
    • New tool “get_merchant_readings” functional
    • “get_merchant_profile” reworded the description of “address” cosmetic
    • Tool “decide_cheapest_model” changed its title: Pre-flight: cheapest listed model for your needs (paid: 0.003 RLUSD via x402) → Pre-flight: cheapest listed model for your needs (paid: 0.003 RLUSD or 0.003 USDC on Base via x402) cosmetic
    • Tool “decide_provider_health” changed its title: Pre-flight: AI provider conditions (paid: 0.001 RLUSD via x402) → Pre-flight: AI provider conditions (paid: 0.001 RLUSD or 0.001 USDC on Base via x402) cosmetic
    • Tool “get_merchant_profile” changed its title: x402 merchant conditions report (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) → x402 merchant readings (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) (alias of get_merchant_readings) cosmetic
    • Tool “get_price_index” changed its title: x402 price index (XRPL) (paid: 0.005 RLUSD via x402) → x402 price index (XRPL) (paid: 0.005 RLUSD or 0.005 USDC on Base via x402) cosmetic
    • Tool “get_pulse_facilitator” changed its title: Pulse: x402 facilitator (paid: 0.001 RLUSD via x402) → Pulse: x402 facilitator (paid: 0.001 RLUSD or 0.001 USDC on Base via x402) cosmetic
    • Tool “get_pulse_providers” changed its title: Pulse: AI providers (paid: 0.001 RLUSD via x402) → Pulse: AI providers (paid: 0.001 RLUSD or 0.001 USDC on Base via x402) cosmetic
    • Tool “get_pulse_storm” changed its title: Pulse: storm signal (paid: 0.001 RLUSD via x402) → Pulse: storm signal (paid: 0.001 RLUSD or 0.001 USDC on Base via x402) cosmetic
    • Tool “paycheck” changed its title: Pay Radar: pre-flight scan of an XRPL x402 endpoint before paying (paid: 0.003 RLUSD via x402) → Pay Radar: pre-flight scan of an XRPL x402 endpoint before paying (paid: 0.003 RLUSD or 0.003 USDC on Base via x402) cosmetic
    • Tool “payradar” changed its title: Pay Radar (alias of paycheck): pre-flight scan of an XRPL x402 endpoint before paying (paid: 0.003 RLUSD via x402) → Pay Radar (alias of paycheck): pre-flight scan of an XRPL x402 endpoint before paying (paid: 0.003 RLUSD or 0.003 USDC on Base via x402) cosmetic
  • 15 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “decide_provider_health” rewrote its description, which is the text the model reads security
    • Tool “get_merchant_profile” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_facilitator” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_providers” rewrote its description, which is the text the model reads security
    • Tool “get_pulse_storm” rewrote its description, which is the text the model reads security
    • Server version: 0.4.1 → 0.4.2 functional
    • Server version: 0.4.0 → 0.4.1 functional
    • “decide_provider_health” reworded the description of “provider” cosmetic
  • 13 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “decide_cheapest_model” rewrote its description, which is the text the model reads security
    • Tool “decide_provider_health” rewrote its description, which is the text the model reads security
    • Tool “get_merchant_profile” rewrote its description, which is the text the model reads security
    • Tool “paycheck” rewrote its description, which is the text the model reads security
    • Tool “paycheck_demo” rewrote its description, which is the text the model reads security
    • Schema quality: 177 → 200 ▼ functional
    • Schema quality: 2482 → 3385 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 0.3.1 → 0.4.0 functional
    • New tool “payradar” functional
    • New tool “payradar_demo” functional
    • New tool “decide_cheapest_model” functional
    • New tool “decide_provider_health” functional
    • New tool “paycheck” functional
    • New tool “paycheck_demo” functional
    • Tool “decide_cheapest_model” changed its title: Decision: cheapest model for your needs (paid: 0.003 RLUSD via x402) → Pre-flight: cheapest listed model for your needs (paid: 0.003 RLUSD via x402) cosmetic
    • Tool “decide_provider_health” changed its title: Decision: AI provider go/no-go (paid: 0.001 RLUSD via x402) → Pre-flight: AI provider conditions (paid: 0.001 RLUSD via x402) cosmetic
    • Tool “get_merchant_profile” changed its title: x402 merchant profile (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) → x402 merchant conditions report (paid: 0.03 RLUSD or 0.03 USDC on Base via x402) cosmetic
    • Tool “paycheck” changed its title: Paycheck: is this XRPL x402 endpoint safe to pay? (paid: 0.003 RLUSD via x402) → Pay Radar: pre-flight scan of an XRPL x402 endpoint before paying (paid: 0.003 RLUSD via x402) cosmetic
    • Tool “paycheck_demo” changed its title: Paycheck demo (free) → Pay Radar demo (free) cosmetic
  • 12 Oct 26 66

    First indexed and scored.

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 18 Oct 2026 · Probed https://mcp.agentweather.io/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentweather.io CN=WE1,O=Google Trust Services,C=US 10 Oct 2026 8 Jan 2027 ECDSA 256 ECDSA-SHA256 1ea4773ac96a68cf1341c68c2189f6da
SANs: agentweather.io, mcp.agentweather.io, *.mcp.agentweather.io
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.agentweather.io. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
io. present 57355 8 Verified
agentweather.io. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.agentweather.io/mcp Verified 200
http (plaintext) http://mcp.agentweather.io/mcp HTTPS enforced 301 https://mcp.agentweather.io/mcp
MCP tools · 21 exposed · ~4,241 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
decide_cheapest_model ~368

Paid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Lowest listed OpenRouter price among models meeting your needs: the lowest-priced match (field `pick`) and the next-lowest from a different vendor, reasons, excluded counts per filter and vendor status-page readings, each with source and time. A price reading, not advice and not about model quality. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
capabilitystring–Comma list, all required: reasoning, coding, vision-input, image-output, audio, free-tier, tools, structured-output
exclude_vendorstring–Comma list of vendors to skip
include_freeboolean–Allow zero-price / :free entries (default false)
max_input_per_1mnumber–Max input price, USD per 1M tokens
max_job_cost_usdnumber–Max cost of 10k input + 1k output tokens, USD
max_output_per_1mnumber–Max output price, USD per 1M tokens
min_contextinteger–Minimum context length in tokens
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.
vendorstring–Comma list of allowed vendors

No output schema declared.

No examples provided.

decide_provider_health ~279

Paid: 0.005 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.005 USDC on Base (eip155:8453). AI provider health reading. Use before an agent calls an AI provider: the vendor's own status-page indicator and active incidents, the share of disturbed checks in the last 24h of our record (checked every 10 min), and a reading (go, caution, no_go, unknown) with a suggested-handling flag. Each reading lists its source and time. Some providers are no longer measured (status null until 2026-11-12). Not affiliated with any source. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.
providerstringyesVendor slug (status feeds: anthropic, morph; others return unknown) or a model id like anthropic/claude-sonnet-4

No output schema declared.

No examples provided.

get_current_conditions ~222

Paid: 0.007 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.007 USDC on Base (eip155:8453). Combined record in one call: AI provider health readings (public status pages and incidents), x402 payment readings on the XRP Ledger (payments, payers, merchants) and XRPL server info, plus GitHub, npm and MCP Registry readings for agent tooling. Raw readings first, each with its source and timestamp; gaps are reported, not filled. Cached up to 5 minutes. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_merchant_profile ~245

Paid: 0.02 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.02 USDC on Base (eip155:8453). For XRP Ledger users: x402 merchant readings for one payee by XRPL address: payments and unique payers in the last 24h from our own XRP Ledger scan, payer mix, account age, first funder and Domain field, endpoint liveness and 402 status, plus a modeled summary score (a measurement, not advice). Each reading lists its source and time. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
addressstringyesXRPL classic address of the payee (payTo) to report on
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_merchant_readings ~246

Paid: 0.02 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.02 USDC on Base (eip155:8453). For XRP Ledger users: x402 merchant readings for one payee by XRPL address: payments and unique payers in the last 24h from our own XRP Ledger scan, payer mix, account age, first funder and Domain field, endpoint liveness and 402 status, plus a modeled summary score (a measurement, not advice). Each reading lists its source and time. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
addressstringyesXRPL classic address of the payee (payTo) to report on
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_model_category ~190

Paid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Conditions for one model category (prices, limits, listing events, vendor status) as declared by public sources. Not a ranking. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
namestringyesModel category
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.
sortstring–Optional sort order

No output schema declared.

No examples provided.

get_model_report ~212

Paid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Conditions report for one AI model as declared by public sources: prices, limits, modalities, listing events and vendor status. Not a ranking and makes no statement about model performance. Find ids with the free list_models tool. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
idstringyesModel id from list_models, e.g. openai/gpt-4o
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_models_sample_yesterday ~52

Free. Returns the day-old change summary of the AI model directory (previous calendar day, America/Chicago): listing, price and status changes as declared by public sources. Not live data. No inputs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_price_index ~166

Paid: 0.005 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.005 USDC on Base (eip155:8453). Observed prices of x402 endpoints settling on XRPL, summarized per asset, with sources and timestamps. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_pulse_facilitator ~204

Paid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Small preflight metric from our own measurement of the t54 x402 facilitator on XRPL mainnet (not affiliated with T54 Labs): ok (boolean), level (ok/degraded/down/unknown), one reason, asOf and sources. Cached up to 30 s. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_pulse_providers ~222

Paid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Small metric summarizing public AI-provider status pages (Statuspage API; currently GitHub and Anthropic): level, one reason, per-provider indicator, asOf and sources with attribution, terms_url and not_affiliated. openai/cursor keys return null until 2026-11-12 (deprecated). Not affiliated with any source. Cached up to 60 s. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_pulse_storm ~255

Paid: 0.001 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.001 USDC on Base (eip155:8453). Small loop-friendly combined reading: the worst current level across tracked public status pages, measured facilitator reachability and recent changes in our record. Returns storm (boolean), level (calm/breezy/unsettled/storm/unknown), one reason, asOf and sources, combining public AI-provider status pages (currently GitHub and Anthropic), our own measurement of x402 facilitator reachability and recent snapshot changes. Each source lists attribution, terms_url and not_affiliated; not affiliated with any source. Cached up to 60 s. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_sample_yesterday ~47

Free. Returns a day-old sample of the conditions report (previous calendar day, America/Chicago) so you can inspect the report format before paying. Not live data. No inputs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_service_status ~58

Free. Returns whether the Agent Weather API and its XRPL payment facilitator are reachable, the API version, and the list of paid routes with their prices and accepted assets (from /.well-known/x402). Returns no report data. No inputs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_x402_activity ~204

Paid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). x402 payment readings on the XRP Ledger from our own scan of validated ledgers: payments and volume per asset for 1h/24h/7d, hourly and daily series, unique payers and merchants, sample transactions, and caveats. Cached up to 60 s. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

get_x402_health_report ~175

Paid: 0.01 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.01 USDC on Base (eip155:8453). Health report for known x402 endpoints and the t54 facilitator: reachability and whether endpoints answer with a valid 402, with timestamps. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.

No output schema declared.

No examples provided.

list_models ~178

Free. Day-old index of the Agent Weather AI model directory: model id, name, vendor and categories only (models first seen at least 24 h ago; flagged in `snapshot`). Live prices, context length, vendor status, 24h/7d changes, job cost and events are in the paid get_model_report and get_model_category tools. Not a ranking. Supports filtering by vendor, category or text query and pagination (limit/offset). Use the ids with the paid get_model_report tool.

NameTypeReqDescription
categorystring–Filter by category
limitinteger–Page size (default 100, max 100)
offsetinteger–Offset for pagination
qstring–Free-text filter on id/name
vendorstring–Filter by vendor slug, e.g. openai

No output schema declared.

No examples provided.

paycheck ~365

Paid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay Radar (weather-radar style pre-flight scan). Use when an agent is about to pay an unfamiliar XRPL x402 endpoint and wants pre-payment signals first. Payment conditions report: raw signals, a coverage block, then a summary of signals (not a recommendation). Fetches its 402 without paying and checks x402 shape, network, asset (RLUSD by issuer), payTo on the XRP Ledger (exists, balance, trust line, age), price sanity, TLS, latency, uptime history and invoiceId. Summary of signals (not a recommendation): checks_passed / review_advised / checks_failed (shown as 'All readings normal', 'Some readings unusual', 'Several readings unusual') with reasons; rule: 2+ fail checks = checks_failed, exactly 1 fail or any warn/unknown = review_advised, none = checks_passed; each check states its method. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
max_usdnumber–Highest price you would pay, USD (default 0.10)
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.
urlstringyesFull http(s) URL of the x402 endpoint to check

No output schema declared.

No examples provided.

paycheck_demo ~92

Free. A full Pay Radar scan (pre-flight payment conditions report: x402 pre-payment signals) result for a fixed example: Agent Weather's own /v1/pulse/facilitator endpoint. Shows the summary of signals (checks_passed / review_advised / checks_failed), reasons and per-check methods before you pay for the paycheck tool on another URL. Cached up to 10 minutes. No inputs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

payradar ~367

Paid: 0.003 RLUSD per call via x402 on XRPL mainnet (xrpl:0), or 0.003 USDC on Base (eip155:8453). Pay Radar (weather-radar style pre-flight scan). Use when an agent is about to pay an unfamiliar XRPL x402 endpoint and wants pre-payment signals first. Payment conditions report: raw signals, a coverage block, then a summary of signals (not a recommendation). Fetches its 402 without paying and checks x402 shape, network, asset (RLUSD by issuer), payTo on the XRP Ledger (exists, balance, trust line, age), price sanity, TLS, latency, uptime history and invoiceId. Summary of signals (not a recommendation): checks_passed / review_advised / checks_failed (shown as 'All readings normal', 'Some readings unusual', 'Several readings unusual') with reasons; rule: 2+ fail checks = checks_failed, exactly 1 fail or any warn/unknown = review_advised, none = checks_passed; each check states its method. Without payment this returns isError with the x402 PaymentRequired object (fresh invoiceId); retry with the signed payload in _meta["x402/payment"] or the payment_signature argument. Unpaid calls cost nothing.

NameTypeReqDescription
max_usdnumber–Highest price you would pay, USD (default 0.10)
payment_signaturestring–Optional. Base64 x402 PAYMENT-SIGNATURE value (signed RLUSD or USDC PaymentPayload) for hosts that cannot set _meta["x402/payment"]. Omit on the first call to receive the payment requirements.
urlstringyesFull http(s) URL of the x402 endpoint to check

No output schema declared.

No examples provided.

payradar_demo ~94

Free. A full Pay Radar scan (pre-flight payment conditions report: x402 pre-payment signals) result for a fixed example: Agent Weather's own /v1/pulse/facilitator endpoint. Shows the summary of signals (checks_passed / review_advised / checks_failed), reasons and per-check methods before you pay for the paycheck tool on another URL. Cached up to 10 minutes. No inputs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Agent Weather MCP server?

Agent Weather is a hosted endpoint at https://mcp.agentweather.io/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 · mcp.agentweather.io

# add to Claude Code
claude mcp add --transport http io-agentweather-agent-weather 'https://mcp.agentweather.io/mcp'
Common questions

What is the Agent Weather MCP server?

Agent Weather is an MCP server listed in the public MCP registry as io.agentweather/agent-weather. Open-source intelligence for AI agents: public readings, each with its source and timestamp. This page covers its hosted endpoint (https://mcp.agentweather.io/mcp).

Is the Agent Weather MCP server safe to use?

Agent Weather scores 72 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 Agent Weather MCP server expose?

Agent Weather exposes 21 tools: get_service_status, list_models, paycheck_demo, payradar_demo, get_sample_yesterday, and 16 more. Their descriptions and schemas cost roughly 4,241 tokens of context every time the server is loaded.

Does the Agent Weather MCP server require authentication?

No. We connected to Agent Weather without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Weather MCP server still maintained?

Agent Weather is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.