# Pubtator (remote · gateway.pipeworx.io) PubTator 3 MCP — biomedical entity search, literature search with entity - Trust score: 62/100 (medium) - Change this week: −11 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-18 > **Recent critical change**: Authorization (2026-10-13). See the changelog below before you install this server. ## Components - remote · `gateway.pipeworx.io`: 62/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp) ## Channel facts - Endpoint: `https://gateway.pipeworx.io/pubtator/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `0.1.0` ## Trust breakdown 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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-18. - **Endpoint Security**: 46/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (forget). - HTTPS check failed: the endpoint is reachable over plaintext HTTP. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 83/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 21369 tokens (~464/item across 46 items; 46 tools + 0 resources), over budget; trim descriptions and params. - Tools include usage examples. - **Stability & Change Management**: 22/100 - Stability check failed: schema churn in the 7 days we've observed: 0 tool removals, 0 breaking changes, 1 auth/transport breaks, 1 additions. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - Structured output schemas are declared (4% of tools); any adoption earns full credit. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 47 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 40/100 - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. ## Install ### How do I install the Pubtator MCP server? Pubtator is a hosted endpoint at https://gateway.pipeworx.io/pubtator/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. ### Claude ```bash claude mcp add --transport http pipeworx-io-pubtator 'https://gateway.pipeworx.io/pubtator/mcp' ``` ### Cursor ```json { "mcpServers": { "pipeworx-io-pubtator": { "url": "https://gateway.pipeworx.io/pubtator/mcp" } } } ``` ### VS Code ```json { "servers": { "pipeworx-io-pubtator": { "type": "http", "url": "https://gateway.pipeworx.io/pubtator/mcp" } } } ``` ### Codex ```toml [mcp_servers.pipeworx-io-pubtator] url = "https://gateway.pipeworx.io/pubtator/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "pipeworx-io-pubtator": { "type": "remote", "url": "https://gateway.pipeworx.io/pubtator/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add pipeworx-io-pubtator --url 'https://gateway.pipeworx.io/pubtator/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: pipeworx-io-pubtator: url: "https://gateway.pipeworx.io/pubtator/mcp" ``` ### Netclaw ```json { "McpServers": { "pipeworx-io-pubtator": { "Transport": "http", "Url": "https://gateway.pipeworx.io/pubtator/mcp" } } } ``` ### Vellum ```bash assistant mcp add pipeworx-io-pubtator -t streamable-http -u 'https://gateway.pipeworx.io/pubtator/mcp' ``` ### Other ```json { "mcpServers": { "pipeworx-io-pubtator": { "type": "http", "url": "https://gateway.pipeworx.io/pubtator/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-18 (score 62, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads ### 2026-10-17 (score 62, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “company_facts” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads - [security] Tool “entity_profile” rewrote its description, which is the text the model reads - [cosmetic] “company_facts” reworded the description of “attribute” ### 2026-10-16 (score 61, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads - [security] Tool “subscribe” rewrote its description, which is the text the model reads - [cosmetic] “subscribe” reworded the description of “params” ### 2026-10-15 (score 61, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads - [functional improvement] Tool “resolve_entity” now declares an output schema - [functional] New tool “company_register_search” - [cosmetic] “ask_pipeworx_grounded” added an optional parameter “prefer_tool” - [cosmetic] “entity_profile” added an optional parameter “country” - [cosmetic] “resolve_entity” added an optional parameter “country” - [cosmetic] “entity_profile” reworded the description of “value” ### 2026-10-14 (score 60, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads ### 2026-10-13 (score 60, +30) - [critical regression] Authorization: unverified → fail - [security regression] Stability: unverified → fail - [security improvement] Injection markers: unverified → pass - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “ask_pipeworx” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads - [security] Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads - [security] Tool “company_facts” rewrote its description, which is the text the model reads - [security] Tool “deep_research” rewrote its description, which is the text the model reads - [functional improvement] Tool coverage: unverified → 100 - [functional improvement] Schema quality: unverified → 100 - [cosmetic] “ask_pipeworx” added an optional parameter “packs” - [cosmetic] “ask_pipeworx_beta” added an optional parameter “packs” ### 2026-10-12 (score 30, −43) - [security regression] Authorization: pass → unverified - [security regression] Tool safety: pass → unverified - [functional regression] Schema quality: 100 → unverified - [functional regression] Tool coverage: 100 → unverified - [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day ### 2026-10-11 (score 73, +43) - [security improvement] Authorization: unverified → pass - [security improvement] Injection markers: unverified → pass - [security] First check of Authorization: pass - [security] First check of Judged manipulation: pass - [functional improvement] Tool coverage: unverified → 100 - [functional improvement] Schema quality: unverified → 100 - [functional] First check of Schema quality: excellent - [functional] First check of Schema quality: fail - [functional] First check of Schema quality: pass - [functional] First check of Destructive annotations: 100 - [functional] First check of Tool coverage: 2 - [functional] First check of Tool coverage: 100 - [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day ## MCP tools (46) ### `ask_pipeworx` (~569 tokens) Ask Pipeworx PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government records, USPTO patents, ATTOM real estate, weather, clinical trials, news, stocks, crypto, sports, academic papers, or anything requiring authoritative structured data with citations. Routes the question to the right one of 6,919 tools across 1820 verified sources, fills arguments, returns the structured answer with stable pipeworx:// citation URIs. Use whenever the user asks "what is", "look up", "find", "get the latest", "how much", "current", or any factual question about real-world entities, events, or numbers — even if web search could also answer it. Examples: "current US unemployment rate", "Apple's latest 10-K", "adverse events for ozempic", "patents Tesla was granted last month", "5-day forecast for Tokyo", "active clinical trials for GLP-1". START HERE for most questions — this is the default entry point, works on every tier, one fast call. Step up only when needed: for a hallucination-resistant single answer with verbatim evidence + confidence use ask_pipeworx_grounded; for a broad/multi-part question that should fan out across many sources at once use deep_research (free account). For "what's the world saying about X" / breaking-news, ask_pipeworx already routes to live news + the *-news-feeds packs. Optionally pass packs:["slug","slug"] to restrict routing to specific sources ("answer this using THESE packs"); omit it for full-catalog routing. Input parameters: - `ask` (string): Alias for question. - `input` (string): Alias for question. - `message` (string): Alias for question. - `packs` (array): OPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_… - `prompt` (string): Alias for question. - `q` (string): Alias for question. - `query` (string): Alias for question. - `question` (string, required): Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases. - `text` (string): Alias for question. ### `ask_pipeworx_beta` (~346 tokens) Ask Pipeworx Beta Beta version of ask_pipeworx: identical universal router (same 6,919 tools, same arguments, same response shape) with candidate routing improvements enabled live whenever one is under test. No candidate is active right now (the last was retired on outcome evidence 2026-07-26), so this currently matches ask_pipeworx exactly. Use it exactly like ask_pipeworx when you want the newest routing; results are compared against the stable router to decide what merges. Falls back to nothing — this IS a full working router, just the experimental edge. Input parameters: - `ask` (string): Alias for question. - `input` (string): Alias for question. - `message` (string): Alias for question. - `packs` (array): OPTIONAL. Restrict routing to these pack slugs (e.g. ["sec-form-d","sec-13f"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_… - `prompt` (string): Alias for question. - `q` (string): Alias for question. - `query` (string): Alias for question. - `question` (string, required): Your question or request in natural language. Accepts query, q, prompt, text, input, ask, message as aliases. - `text` (string): Alias for question. ### `ask_pipeworx_grounded` (~336 tokens) Ask Pipeworx — Grounded Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 6,919 across 1820 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups. Input parameters: - `ask` (string): Alias for question. - `input` (string): Alias for question. - `message` (string): Alias for question. - `prefer_tool` (string): Run this exact tool instead of letting the router choose — use a name from a previous answer's alternatives[]. Arguments are still filled from your question. Unknown names are refused, never guessed. - `prompt` (string): Alias for question. - `q` (string): Alias for question. - `query` (string): Alias for question. - `question` (string, required): Your question in natural language. Accepts query, q, prompt, text, input, ask, message as aliases. - `text` (string): Alias for question. ### `search_within` (~238 tokens) Search Within a Source Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged). Input parameters: - `limit` (number): Max passages to return (1-20, default 5). - `query` (string, required): Natural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin". - `text` (string, required): The document text to search inside (max ~200K chars). ### `deep_research` (~638 tokens) Deep Research ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1820 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 6,919 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s). Input parameters: - `ask` (string): Alias for question. - `depth` (string): How many facets to research in parallel: quick=3 (single hop), standard=3 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=6 (pa… - `input` (string): Alias for question. - `message` (string): Alias for question. - `prompt` (string): Alias for question. - `q` (string): Alias for question. - `query` (string): Alias for question. - `question` (string, required): The research question, in natural language. Broad/multi-part is fine — decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases. - `text` (string): Alias for question. ### `discover_tools` (~260 tokens) Discover Tools Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what tools exist for: SEC filings, financials, revenue, profit, FDA drugs, adverse events, FRED economic data, Census demographics, BLS jobs/unemployment/inflation, ATTOM real estate, ClinicalTrials, USPTO patents, weather, news, crypto, stocks. Returns the top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed. Call this FIRST when you have many tools available and want to see the option set (not just one answer). Input parameters: - `description` (string): Alias for query. - `limit` (number): Maximum number of tools to return (default 20, max 50) - `q` (string): Alias for query. - `query` (string, required): Natural language description of what you want to do (e.g., "analyze housing market trends", "look up FDA drug approvals", "find trade data between countries"). Accepts task, q, description, search as… - `search` (string): Alias for query. - `task` (string): Alias for query. ### `resolve_entity` (~654 tokens) Resolve Entity "What's the ticker for…" / "find the CIK for…" / "what's the LEI for…" / "what's the RxCUI for…" / "look up the ID for…" / "what is X's official identifier" / "who owns X" / "is X a subsidiary of Y" — resolve a user-spoken NAME to the canonical/official identifiers other tools require as input. Use FIRST whenever you have a name but need an ID. SUPPORTED TYPES: "company" (cross-source identity spine: 10-digit CIK + ticker + company_name from SEC EDGAR, legal-entity LEI from GLEIF with parent/ultimate-parent/children ownership when the LEI resolves, and security FIGI from OpenFIGI — by exact ticker map when a ticker is implied, and otherwise by name search, so NON-EQUITY instruments that never have a ticker (municipal and corporate bonds, notes, authority debt) DO resolve here; when a name matches more than one instrument it asserts nothing and returns `figi_candidates` to pick from, which is the correct answer to an issuer name that does not identify a single bond; every identifier is labelled with the source that established it, and an identifier that could NOT be resolved is stated explicitly under `unresolved` rather than omitted — accepts ticker, CIK, ISIN, or company name as input; an ISIN like "CH0038863350" resolves to the LEGAL ENTITY that issued the security via the GLEIF ISIN-to-LEI mapping, covering non-US issuers EDGAR cannot reach), "drug" (returns RxCUI + ingredient + brand from RxNorm + pipeworx://rxnorm/concept/{rxcui} citation; accepts brand or generic name). LEI/FIGI enrichment degrades gracefully — if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return. Each call cascades through several lookup endpoints internally — using resolve_entity replaces 2-3 manual lookups. Input parameters: - `country` (string): OPTIONAL ISO 3166-1 alpha-2 of the country whose business register you mean ("NO", "FI", "JP", "GB", "FR", "EE", "BR"). Narrows the national-register fan-out and is often the difference between the r… - `type` (string, required): Entity type: "company" or "drug". - `value` (string, required): For company: ticker (AAPL), CIK (0000320193), or name. For drug: brand or generic name (e.g., "ozempic", "metformin"). Pass the ENTITY NAME ONLY — for a bond that is the ISSUER exactly as printed ("N… Output parameters: - `brand` (string) - `candidates` (array): Rivals, best first. Populated on "ambiguous" and on "matched" alike. - `cik_withheld` (string): A CIK that came back from a FUZZY SEC name match and is NOT asserted, because the spine matched a stronger non-US candidate. The number is here so a caller who wanted the US filer can still use it; w… - `fanout_incomplete` (object): Present IFF at least one register in `searched[]` carried an `error` — set even when `match_status` stayed "ambiguous". `withheld_match` is the candidate this call declined to ASSERT because a regist… - `figi_withheld` (string): A FIGI that matched this name in OpenFIGI (`figi_match: "name_search"`) and is NOT asserted, because `match_status` is "incomplete": a name search cannot tell a company apart from a security carrying… - `ids` (object): Every identifier established: cik, ticker, company_name, lei, figi, isin, cusip, register_id, register_country. A key absent here appears in `unresolved` with a reason — never silently dropped. - `ingredient` (string) - `match_explanation` (string): Plain words. Always present when the spine ran, and required on "ambiguous" and "no_match". - `match_scoring` (object): The margin rule's own inputs, so a caller can see WHY it fell where it did. - `match_status` (string): The headline to branch on. "ambiguous" is an ANSWER, not a failure: two companies matched the name equally well and both are in `candidates`. "no_match" means every register in `searched` was asked a… - `notes` (string) - `query` (string) - `registers` (array): The matched entity as every register that carries it — the match (flagged `matched: true`) plus anything that collapsed into it. A Companies House number AND the LEI that crosswalks to it are the SAM… - `related` (array): Entities that collapsed INTO the match, each carrying `collapsed_by`. - `resolved` (boolean): At least one identifier was established. Read `match_status` and `unresolved` for WHICH — a company can be resolved in a national register with no CIK at all. - `resources` (object) - `searched` (array): EVERY register asked, with its own as-of date and row count. A register that could not be reached carries `error` — 0 rows with an error is "we could not ask", 0 rows without one is "nothing is there… - `sec_alternatives` (array): EDGAR's own discarded near-misses on a name match, surfaced instead of dropped. - `sources` (object): Per-identifier provenance. Every key in `ids` has a matching key here. - `type` (string) - `unresolved` (object): Per-identifier reason an id could NOT be established — the honest twin of `ids`. ### `compare_entities` (~264 tokens) Compare Entities "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups. Input parameters: - `type` (string, required): Entity type: "company" or "drug". - `values` (array, required): For company: 2–5 tickers/CIKs (e.g., ["AAPL","MSFT"]). For drug: 2–5 names (e.g., ["ozempic","mounjaro"]). ### `subscribe` (~943 tokens) Subscribe to Alerts Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id. Requires a Pipeworx OAuth account (anonymous + BYO cannot persist subscriptions). Supported types: "sec_8k" (8-K filings matching ticker + item codes — e.g. items:["5.02"] = officer change), "polymarket_edge" (Polymarket↔Kalshi cross-venue mispricings — params:{topic:"fed"}), "fred_series" (new FRED observations — params:{series_id:"UNRATE"}), "patent_grant" (new USPTO grants for an applicant), "clinical_trial" (new/updated ClinicalTrials.gov studies), "form_d" (new SEC Form D fundraise notices — params:{state?, industry?, min_amount?, exemption?}, all optional), "news_keyword" (GDELT keyword news alerts, metadata+link only — params:{query, lang?, domains?}), "job_post" (new public job-board postings — params:{ats?, board_token?} or {domain?}, plus optional title_query/location_query), "tool_diff" (re-runs any read-only tool on a schedule and fires on change — params:{tool, args?, fields[], schedule}), "new_entity" (new business registrations from a state business-entity registry — params:{state:"CO", name_query?, entity_type?}), "tech_change" (a watched domain's website technology stack adds or drops a technology — params:{domains:["acme.com"], technologies?}). Delivery channels: feed (always on — pull via recent_alerts or GET registry.pipeworx.io/alerts.json), and optionally email (set delivery:{email:"you@x.com"}) or sms (delivery:{sms:"+15551234567"} — phone must be verified at /account first; 10/day cap). Input parameters: - `delivery` (object): Optional delivery channels in addition to the always-on persistent feed. {email:"you@x.com"} sends a templated alert per fired event. {sms:"+15551234567"} sends an SMS per event — must match the veri… - `params` (object, required): Type-specific filter. sec_8k: {ticker:"AAPL", items?:["5.02","1.01"]}. polymarket_edge: {topic:"fed", min_spread_bps?:500}. fred_series: {series_id:"UNRATE"}. patent_grant: {applicant:"Apple Inc."}.… - `type` (string, required): Subscription type. ### `unsubscribe` (~60 tokens) Unsubscribe from Alerts Cancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its historical events stay available via recent_alerts. Input parameters: - `id` (string, required): Subscription id (uuid) returned by subscribe. ### `list_subscriptions` (~72 tokens) List Subscriptions List the caller's active subscriptions. Returns id, type, params, created_at, last_fired_at, fire_count for each. Use this to review what you're monitoring before adding more or to find an id to cancel. Input parameters: - `include_inactive` (boolean): Include cancelled subscriptions in the response (default false). ### `recent_alerts` (~204 tokens) Recent Alerts Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards. Input parameters: - `limit` (number): Max events to return (1-200, default 50). - `mark_read` (boolean): Flag the returned events read in the same call (default false). - `since` (string): Optional ISO timestamp — return events fired_at >= this time. - `type` (string): Optional — filter to one subscription type. - `unread_only` (boolean): Return only events where read_at is null (default false). ### `entity_profile` (~868 tokens) Entity Profile "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO patents, federal contracts (USAspending), FDA-licensed biologics (Purple Book), H-1B hiring (DOL LCA), news and GLEIF, and returns: cik + company_name (+ resolved_from/resolved_to when `value` was a name); recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (the latest ANNUAL Revenues, NetIncomeLoss, Cash, diluted EPS, capex and operating cash flow, each with its period_end, SEC form and the accession of the filing it came from — plus EntityCommonStockSharesOutstanding, which is the newest COVER-PAGE share count the filer has published rather than an annual one, so its period_end is a cover date after the quarter closed and it is the right per-share denominator; a filer tagging a fallback concept appears under the name of that tag instead, e.g. PaymentsToAcquireProductiveAssets instead of PaymentsToAcquirePropertyPlantAndEquipment); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); federal_contracts (USAspending awards where the company is the recipient); fda_products (FDA-licensed biologics — vaccines, cell/gene therapies — from the Purple Book; a company with only small-molecule/generic drugs will show none here, that is expected, not a failure); hiring (H-1B sponsorship volume + salary range from DOL LCA filings); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. `sources_used` / `sources_failed` say which of these actually returned data for THIS company — an empty section is a real "no data", not a bug. `sources_skipped` is the third state: a leg we deliberately did NOT run, each e… Input parameters: - `country` (string): OPTIONAL ISO 3166-1 alpha-2 of the business register you mean ("NO", "FI", "GB", "JP", "FR", "EE", "BR"). Only affects a NAME lookup, and is often what separates the company you mean from a US namesa… - `type` (string, required): "company" or "ticker" — both are accepted and behave identically; `value` can be a ticker, CIK, or company name either way. person/place coming soon. - `value` (string, required): Ticker (e.g., "AAPL"), zero-padded CIK (e.g., "0000320193"), or company name (e.g., "Moderna"). A NAME now resolves through the national business registers as well as SEC EDGAR, so a non-US company r… ### `recent_changes` (~320 tokens) Recent Changes "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window. Input parameters: - `since` (string, required): Window start — ISO date ("2026-04-01") or relative ("7d", "30d", "3m", "1y"). Use "30d" or "1m" for typical monitoring. - `type` (string, required): Entity type. Only "company" supported today. - `value` (string, required): Ticker (e.g., "AAPL") or zero-padded CIK (e.g., "0000320193"). ### `validate_claim` (~370 tokens) Validate Claim "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. Company-financial claims (revenue, net income, cash for public US companies) verify via the structured SEC EDGAR + XBRL fast path with exact percent-delta math; ANY OTHER factual claim (macro statistics, rates, prices, drug data, records) automatically falls through to the grounded pipeline — routed to the right live source, answered with verbatim evidence, then judged. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the grounded or structured actual value with pipeworx:// citation, and reasoning. IMPORTANT for callers: could_not_verify means the check did not happen (our LLM or source failed) and carries verification_error{stage,detail} — it is NOT evidence for or against the claim, and must not be shown as one. unsupported means we looked and cover no source for it. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison). Input parameters: - `claim` (string, required): Natural-language factual claim, e.g., "Apple's FY2024 revenue was $400 billion" or "Microsoft made about $100B in profit last year". - `tolerance_pct` (number): Max percent deviation still graded approximately_correct (0.5–50). Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted.… ### `company_facts` (~1150 tokens) Company Facts TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period — "Apple revenue for fiscal 2023", "Walmart net income FY2026 Q3", "Microsoft cash at the end of fiscal 2024". PREFER OVER entity_profile / get_company_financials whenever the period matters: those answer "the most recent figures" and will happily hand back FY2025 when you asked about FY2019, and neither separates a discrete quarter from a year-to-date figure. This one refuses instead — it NEVER substitutes the latest period for the period requested, NEVER returns 0 for missing data, NEVER lets a 9-month YTD number answer a quarterly question, and NEVER converts a currency. Every answer carries the exact us-gaap concept it came from, what that concept MEASURES (NetIncomeLoss excludes non-controlling interests, ProfitLoss includes them — not synonyms), the accession number and a link to the filing on sec.gov, the restatement trail of any superseded figures, and a contract + derivation version to pin against. Fiscal periods are the FILER'S OWN, anchored on their fiscal-year end, so Walmart's year ending 2026-01-31 is FY2026 and Apple's ending 2025-09-27 is FY2025. Attributes: revenue, net_income, cash, gross_profit, operating_income, eps_diluted, capex, operating_cash_flow, long_term_debt, shares_outstanding (the dei COVER-PAGE share count, so its period end is the cover date, after the quarter closed — that is the most current count the filing carries). Units are not all USD: shares_outstanding is in `shares` with currency null, eps_diluted in `USD/shares`. A discrete quarter the filer never filed — every Q4, and Q2/Q3 of cash-flow lines, which are filed year-to-date — is DERIVED as YTD(q) minus YTD(q-1) and comes back with `reported: false`, the subtraction named in `derivation` (fy_minus_9m / ytd_9m_minus_6m / ytd_6m_minus_3m) and both legs with their filings in `derived_from`; test `reported` if you will only accept a figure lifted from a filing. Per-share and ba… Input parameters: - `as_of` (string): Past ISO timestamp with timezone. Replay the latest answer actually recorded by that instant; no invented history or live fallback. - `attribute` (string, required): Which figure. "revenue" = total consolidated revenue; "net_income" = net income (loss); "cash" = cash and cash equivalents at the period end; "gross_profit"; "operating_income"; "eps_diluted" (dilute… - `basis` (string): Only "consolidated" in v1. Segment and product-level figures are XBRL-dimensioned and are not reachable through this contract at any concept. - `company` (string, required): Ticker ("AAPL"), 10-digit CIK ("0000320193"), or company name. A name that matches two filers equally well returns status "ambiguous" with both named rather than guessing — pass a ticker or CIK to be… - `exclude_publishers` (array): Publisher ids forbidden for fact retrieval: sec, fmp, alphavantage. Case and surrounding whitespace are normalized; unknown ids are refused. Excluding sec currently leaves no eligible fact source and… - `freshness` (string): cached (default) permits an eligible stored answer; fresh requires an upstream refresh and never silently falls back to stale data. - `max_age` (number): Maximum age in seconds of the upstream publication, not our fetch. Older or undated facts are withheld. - `period` (object, required): The reporting period, stated explicitly. There is no default and no "latest" — that is the point of this tool. - `restatement` (string): Default "as_amended" — the latest filed figure for the period, with everything it superseded listed. "as_originally_reported" takes the first filing instead. ### `company_register_search` (~664 tokens) Company Register Search Search the NATIONAL BUSINESS REGISTERS by company name and get the register's own id back — a Companies House number, a Norwegian organisasjonsnummer, a Finnish business id, a SIREN, a Japanese corporate number, an Estonian registry code, a CNPJ, or an LEI. Use this when you want the OFFICIAL REGISTERED ENTITY and the country is not the US, or when you do not know which country it is. Registers searched: Companies House (GB), Enhetsregisteret (NO), PRH/YTJ (FI), Sirene (FR), 法人番号公表サイト (JP), RIK e-Business Register (EE), and the GLEIF LEI crosswalk, which reaches jurisdictions we have no register pack for (DE, SE, AU, SG...). THIS TOOL REFUSES TO GUESS, and that is its point: when two different companies match a name equally well it answers `match_status: "ambiguous"` with BOTH, rather than naming one. A one-word trading name usually IS ambiguous — "Bolt", "Apple", "Next", "Sea", "DNB" each match a well-known group AND unrelated micro-entities whose registered name is exactly that word — so pass `country` when you know it. Every response names EVERY register it asked under `searched[]`, with that register's own as-of date and row count, and a register that could not be reached carries an `error` there rather than reading as zero rows: "we could not ask Companies House" is never the same answer as "this company is not in Britain". `related[]` holds entities that collapsed INTO the match — the same company seen through another register, or another country's arm sharing its LEI — so a multinational returns one answer rather than tying with itself. NOT A PEOPLE SEARCH: sole traders and other natural persons are excluded on the publisher's own legal-form field, never guessed from the shape of a name. For US public companies prefer resolve_entity (CIK + ticker + FIGI); the two share this same matcher, and resolve_entity returns these register fields too. Input parameters: - `country` (string): OPTIONAL ISO 3166-1 alpha-2 of the register you mean ("GB", "NO", "FI", "FR", "JP", "EE", "BR"). Narrows the fan-out, and is frequently the difference between an answer and `ambiguous` on a short nam… - `limit` (number): Maximum candidates to return, 1-50 (default 10). Does not change which registers are asked, only how many rivals come back. - `name` (string, required): The company name as you have it, in its own script. Pass it VERBATIM — do not strip the legal form ("Oyj", "AS", "株式会社", "Ltd"): in Japanese the form is a PREFIX as often as a suffix and 株式会社花王 and 花… ### `scan_dependency` (~254 tokens) Scan Dependency Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history) and bundlephobia (gzipped/minified bundle size, dependency count, ESM/tree-shake support). Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me". Returns a summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions. NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly. Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns. Input parameters: - `package` (string, required): npm package name. Scoped packages (e.g. "@types/node") are accepted. - `version` (string): Specific version to check (e.g., "18.3.1"). Defaults to the latest published version when omitted. ### `bet_research` (~1128 tokens) Bet Research Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), a polymarket.com URL, or a question text. Prefer an UNDATED slug: a dated one ("...-by-june-30-2026") stops resolving the day it settles, because Polymarket de-indexes resolved markets. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is f… Input parameters: - `depth` (string): quick = 2-3 evidence sources, thorough = full fan-out. Default thorough. - `include_raw` (boolean): Default false. When false (recommended), FRED/FDA/GDELT/Federal-Register evidence is summarized to the few fields agents actually use — keeps responses under ~20KB. Pass true to get full upstream pay… - `market` (string, required): Polymarket slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), full URL ("https://polymarket.com/event/..."), or question text ("Will Bitcoin hit $150k?"). Dated slugs stop res… ### `polymarket_arbitrage` (~876 tokens) Polymarket Arbitrage Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FEES: every opportunities[] row and partition_check.arbitrage carry edge_pp_gross (== gap_pp / overround_pp), fees_pp, edge_pp_net, net_positive, plus polymarket_fee_pp, fee_basis and fee_categories[]. BOTH cost components are modeled: Polymarket's own per-category TAKER FEE (fee = shares × rate × p × (1-p), rates crypto 0.07 / sports-economics-culture-weather-other 0.05 / finance-politics-mentions-tech 0.04, geopolitics and world events fee-free; verified against Polymarket's own… Input parameters: - `event` (string): Single-event mode (use this if you know the specific Polymarket event): event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k". Full Polymarket URLs also accepted. - `topic` (string): Cross-event mode (use this if you want to scan related events across the platform): a topic or seed question like "Fed rate decision" or "Strait of Hormuz traffic returns to normal". Tool searches Po… ### `polymarket_edges` (~1110 tokens) Polymarket Edges Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (net of slippage AND Polymarket's own taker fee — fees_pp_applied itemises the fee component; see fees.ts for the published per-category schedule), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge — your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking — 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates,… Input parameters: - `category_filter` (string): Comma-separated list to restrict the output: "model_driven" (crypto_price + news_momentum), "structural_arbitrage" (partition_overround), "concentrated_longshot". Combine like "model_driven,structura… - `limit` (number): Top N edges to return after ranking. Default 10, max 25. - `max_spread_pp` (number): Tradeable-edge filter. Maximum bid/ask spread in percentage points on the representative market. Default null (no filter). Set to 2 to require tight books — anything wider eats most plausible edges. - `min_edge_pp` (number): Minimum |edge| in percentage points to include (default 0.5). Edge is evaluated NET of slippage and Polymarket's own taker fee. - `min_kelly` (number): Minimum half-Kelly fraction (as decimal, e.g. 0.005 = 0.5% of bankroll) to include single-leg opportunities. Default 0 (no filter). Skips opportunities that are too small to bet sensibly even if the… - `min_liquidity` (number): Tradeable-edge filter. Minimum $ liquidity on the representative market (or for partition_overround, on at least one top_leg). Default 0 (no filter). Set to 5000 to drop thin-book opportunities where… - `min_partition_leg_kelly` (number): Minimum BEST per-leg half-Kelly fraction across a partition_overround opportunity's top_legs (or longshot_basket legs). Default 0 (no filter). Partition arbs always return kelly_fraction_half=0 at th… - `slippage_pp` (number): Assumed execution slippage in percentage points per leg (default 0.3), for bid/ask + thin depth cost that a last-trade price does not show. Subtracted from raw |edge| before ranking and Kelly sizing,… - `window` (string): Polymarket volume window to filter markets. Default 1wk. ### `polymarket_kalshi_spread` (~1683 tokens) Polymarket–Kalshi Spread Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 11 pre-mapped macro subjects ("fed", "btc", "eth", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. You do NOT have to use those exact keys: the topic is resolved through aliases and keywords, so "bitcoin", "fed rate decision", "inflation", "s&p 500" and "next pope" all land on the right subject, and `resolution.topic_matched_by` tells you whether it was an exact key, a known alias, a phrase found inside a longer question, or a single-keyword guess — treat "phrase" and "token" as a GUESS at what you meant. An unresolvable topic returns error:"mapping_failed" with mapping_stage:"topic_unrecognized" and known_topics[]; it never silently falls back to a default subject. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. `resolution` is returned in BOTH modes and says how each side's identifier was picked (which Kalshi series was queried, how many events came back, whether the chosen one had quoted markets; which Polymarket search query ran and why that event won). Fleet #2064: when two Polymarket candidates tie on resolution time `polymarket_selected_by` now SAYS so, names every tied slug, names the tie-break that actually decided it (the candidate whose metric_type matches the Kalshi series, else lexicographic slug order), and states whether the winner's metric matches the Kalshi series — it used to assert "picked the soonest-resolving" byte-identically on calls that returned DIFFERENT events, because the tie was settled by upstream fetch arrival orde… Input parameters: - `kalshi_event_ticker` (string): Explicit Kalshi event ticker, e.g. "KXFED-26OCT". Overrides the topic-mapped Kalshi side. - `polymarket_event_slug` (string): Explicit Polymarket event slug, e.g. "fed-decision-in-june-825". Overrides the topic-mapped Polymarket side. - `topic` (string): Subject to compare. Canonical keys: fed | btc | eth | cpi | gdp | sp500 | recession | next_pope | next_uk_pm | next_israel_pm | 2028_president — but aliases and keywords resolve too ("bitcoin", "fed… ### `polymarket_fill_risk` (~557 tokens) Polymarket Fill Risk Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of `market` (single-market mode) or `event` (basket/partition mode). SINGLE-MARKET: pass a market slug/URL + side (buy_yes|sell_yes|buy_no|sell_no, default buy_yes) + size_usd (default 1000 — max spend on buys, target proceeds on sells); walks the ladder and returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, and a verdict (clean|degraded|cannot_fill). BASKET: pass an event slug/URL + side (sell_yes = capture overround by selling every leg, buy_yes = capture underround; default auto from partition sum) + size_usd interpreted as settlement notional S (shares per leg; each share pays $1); returns theoretical_sum vs realizable_sum (top-of-book vs VWAP across all legs), capture_ratio, profit_usd at executed size, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk naming the legs most likely to strand you unhedged. USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500 — theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position (the dominant loss mode in real arb-bot P&L). FEES ARE NOT MODELLED HERE: vwap_fill_price/profit_usd are GROSS of Polymarket's own taker fee (rate 0.04-0.07 by category — see polymarket_edges/fees.ts), on top of which this tool prices depth-crossing cost; a thin-margin fill that looks clean here can still be net-negative after the fee. Input parameters: - `event` (string): Basket mode: event slug or full polymarket.com URL — checks every leg of the partition. - `market` (string): Single-market mode: market slug or full polymarket.com URL. - `side` (string): Single-market: buy_yes | sell_yes | buy_no | sell_no (default buy_yes). Basket: sell_yes | buy_yes (default auto — sell if partition sum > 1, buy if < 1). - `size_usd` (number): Single-market: USD to spend (buys) or target proceeds (sells). Basket: settlement notional — shares per leg, each paying $1 at resolution. Default 1000, clamp 10–1,000,000. ### `polymarket_edge_tracker` (~343 tokens) Polymarket Edge Tracker Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinking?" — a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a reason nobody is willing to take). Args: days (lookback, default 14, max 30), window (snapshot family, default "1wk"). RESPONSE: tracked[] = every opportunity in the LATEST snapshot with its full edge_pp_net time-series across prior snapshots, first_seen, trend (new | widening | stable | decaying) and decay_pp_per_day (both computed on |edge_pp_net| — the value itself is signed by trade direction, negative = SELL YES); expired[] = opportunities that appeared in earlier snapshots but are GONE from the latest (closed, resolved, or arbed away) with their lifespan_days — the median lifespan is your competition clock; snapshot_dates[] = which days actually have data (snapshots are written when polymarket_edges runs on a cache-miss, so gaps mean nobody scanned that day). LIMITS: history depth is bounded by the 60-day snapshot TTL and starts from when snapshotting was enabled; decay numbers come from daily closes of edge_pp_net (net of default slippage AND Polymarket's own taker fee — see polymarket_edges), not intraday. Input parameters: - `days` (number): Lookback in days (default 14, clamp 2-30). - `window` (string): Which polymarket_edges window family to read snapshots for: 24hr | 1wk | 1mo (default 1wk). ### `kalshi_weather_edge` (~916 tokens) Kalshi Weather Edge Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one city and settlement date with market_prob (mid), forecast_prob, and edge_pp per strike, plus the settlement clause verbatim. BACKTEST (`backtest_days: N`): scores an archived gridded forecast against the market on settled days and returns brier_market vs brier_forecast with a plain-English `verdict`, so the edge is MEASURED rather than asserted. READ THE WARNINGS — they are not boilerplate. (1) These markets DO NOT settle on the NWS. They settle on The Weather Company (weather.com) at a Kalshi station code such as CLINYC, which the response quotes verbatim; so part of every edge_pp is NWS-vs-Weather-Company disagreement about the same day at the same station, which is not mispricing and not tradeable. `settlement_vs_forecast_basis_f` from backtest mode is that part as a number. (2) The station is DERIVED from the settlement clause, never from the city name: Chicago settles at MIDWAY and New York at CENTRAL PARK, so a city-centre forecast would misprice a whole ladder. A station that cannot be resolved yields rows with no forecast and a reason, never a guessed coordinate. (3) forecast_prob assumes a normal distribution around the NWS high whose width is ASSUMED, not fitted (stated in `distribution_assumption`) — run backtest mode to see whether it is calibrated. (4) edge_pp is gross: no Kalshi fees, no bid-ask. MEASURED RESULT, AND IT IS NOT THE FLATTERING ONE: on the first backtest (KXHIGHNY, 13 settled days to 2026-09-11, 58 market observations) the MARKET beat the forecast — Brier 0.1008 for the market against 0.1594 for the archived gridded forecast, lower being better. So on that sample there is NO forecast edge to sell, and a large edge_pp is more likely to be the model disagreeing with a better-informed market than an opport… Input parameters: - `backtest_days` (number): Run measurement mode over the last N settled days (max 60) instead of pricing today. Returns brier_market vs brier_forecast, the settlement-vs-forecast basis, and per-day detail. Both sides are score… - `city` (string): City to price, e.g. "nyc", "chicago", "los angeles", "miami", "austin", "houston", "denver", "philadelphia". Defaults to nyc. Unmapped cities return known_cities[] rather than a wrong series. - `date` (string): Settlement date as YYYY-MM-DD. Defaults to the soonest open event. Daily weather markets open ~1-2 days ahead and close 05:00Z the next day. - `market_type` (string): "high_temp" (default) | "precip". Precipitation markets return prices but no forecast_prob yet. - `series_ticker` (string): Explicit Kalshi series, e.g. "KXHIGHNY" or "KXHIGHTBOS" (Boston). Overrides `city`; use it for any of the 121 daily weather series not in the city list. ### `resolution_audit` (~410 tokens) Resolution Audit Extract the settlement clause of a single Polymarket or Kalshi market: who publishes the settling number (source), the clock time + timezone it is taken at, the precision of the computation (e.g. "1-minute candle close" vs "60-second trailing average" vs "election outcome"), the evidence standard (official_source | consensus_reporting | any_credible_report | unspecified), and void_handling (cancellation/postponement settlement — reused verbatim from bet_research's cancellation_rule detector, not re-derived). Parses Polymarket's `description` field (fetched via polymarket_market) or Kalshi's `rules_primary` + `rules_secondary` fields (fetched via kalshi_market) with regex + a small vocabulary — no LLM pass, so an unusual clause reports confidence:"low" rather than a guess. Pass `market` as a Polymarket slug/URL or a Kalshi market ticker (e.g. "KXBTCD-26SEP1317-T66999.99"); a Kalshi EVENT ticker (e.g. "KXBTCD-26SEP1317") also works — it picks one representative market under that event, since the settlement mechanism is normally shared across all strikes/legs in one event. Use this before treating a polymarket_kalshi_spread row as a real arbitrage: two ladders that look alike can settle on different sources, at different times, with different precision — this tool is how you check. Pair with resolution_diff to compare two markets directly. KNOWN GAP: idiosyncratic phrasing that doesn't match the vocabulary returns confidence:"low" and evidence_standard:"unspecified" rather than an LLM-guessed answer. Input parameters: - `market` (string, required): Polymarket market slug or URL, OR a Kalshi market ticker (preferred) or event ticker (falls back to a representative market under that event). - `venue` (string, required): Which venue to fetch the market from. ### `resolution_diff` (~330 tokens) Resolution Diff Field-by-field diff of TWO markets' settlement clauses (one from each of `a` and `b`; either can be Polymarket or Kalshi) — runs resolution_audit on both sides and compares source, settle time, precision, and evidence standard. Returns `equivalent`: "true" only when both sides parsed with enough confidence to compare AND no field conflicts; "false" when a specific conflict was found (differing_fields names which — e.g. ["source","settle_time"] for a Polymarket Bitcoin market settling on Binance's 1-minute candle at noon ET versus a Kalshi KXBTCD market settling on CF Benchmarks' BRTI 60-second average at 5pm EDT — SAME asset, DIFFERENT contract); "unclear" when one or both sides could not be confidently parsed (an absence of evidence is not evidence of equivalence — read raw_clause yourself in that case). Only flags a field as differing when BOTH sides gave a SPECIFIC comparable answer — a named source (e.g. "Associated Press, Fox News, NBC") against a generic one (e.g. Kalshi's "consensus of media organizations") is treated as the same evidence standard, not a conflict, since that is standard election-market boilerplate on both venues. Use this before sizing a polymarket_kalshi_spread pair as a real cross-venue arb, or standalone to sanity-check any two markets you suspect settle on different things. Input parameters: - `a` (object, required): First market to compare. - `b` (object, required): Second market to compare. ### `release_calendar_markets` (~851 tokens) Release Calendar Markets JOIN of the official release calendar (econ data, the FOMC, FDA decisions, SEC rules) against LIVE Polymarket/Kalshi markets — which scheduled releases land in the next N hours, and which live markets resolve on them. This is a POSITIONING tool, not a speed product: results are cached like every other pack (≤ 60s TTL) and there is no push/webhook — do not use this to try to beat a release, use it to see what is coming and what is already priced. CATEGORIES: econ (CPI, Employment Situation/jobs report, GDP, PCE, PPI, retail sales, housing starts, jobless claims — via fred_release_dates per known release_id, since FRED's own cross-release calendar mostly returns recent actuals, not future dates), fed (the next FOMC meeting's rate decision, via fomc_calendar), fda (PDUFA action dates + FDA advisory-committee meetings, via pdufa_catalysts / fda_adcom_calendar), sec (SEC final rules whose own DATES clause names an effective date in the window, via federal-register recent_rules — usually finds nothing in a short window since SEC rules typically take effect 30–60 days out, which is an accurate answer, not a bug), court (ALWAYS EMPTY today — court-listener has no forward-looking scheduled-hearing calendar, only filing/termination dates, so this category returns zero releases with unsupported:true rather than fabricate one). Omit `categories` or pass "all" for every category. MATCHING AND ITS HONESTY CONTRACT: every release is returned even when it has ZERO matched markets — a release is never dropped just because nothing on Polymarket or Kalshi resolves on it (most FDA/SEC releases will show markets:[]; that is signal, not a gap). Every matched market carries resolves_on_this_release: "true" (the venue's own close/end date sits within ~36h of the release AND the question passed a subject filter — econ and fed only), "likely" (same subject filter, but the venue closes days away from the release date), or "unclear" (a keyword hit with no date to anchor against — always true… Input parameters: - `categories` (string): Comma or space separated subset of econ|fed|fda|sec|court, or "all" (default). E.g. "econ,fed" or "fda". - `hours` (number): Look-ahead window in hours from now. Default 48. Capped at 720 (30 days) — econ/fed releases are dated weeks apart, so a short window is often empty; widen rather than assume nothing is scheduled. Output parameters: - `as_of` (string) - `categories` (array) - `empty_reason` (string): Present ONLY on a zero-release window: "no_releases_in_window". The window was queried and nothing is scheduled — this is an answer, not a failure. - `hint` (string): Present ONLY on a zero-release window: what to change (usually a wider `hours`). - `notes` (array) - `release_count` (number) - `releases` (array) - `releases_with_matched_markets` (number) - `window` (object) ### `archive_evidence` (~374 tokens) Archive Evidence What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates. Input parameters: - `date` (string, required): The date to look up, as YYYY-MM-DD (e.g. "2023-06-01"), YYYYMMDD, or a full ISO timestamp. - `max_chars` (number): Characters of page text to return. Default 12000, max 60000. - `max_gap_days` (number): Furthest a capture may be from the date and still be used, in days. Default 30, max 3650. - `url` (string, required): The page address, e.g. "https://www.sec.gov" or "https://www.ftc.gov/policy-notices/privacy-policy". ### `archive_compare` (~301 tokens) Archive Compare What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawl, Arquivo.pt), extracts the readable text of both, and returns a text-level diff: the segments removed and added, a similarity score, and both capture timestamps with their gaps from the requested dates. It diffs readable text, not markup, so a restyled page with the same words reads changed:false. Identical captures answer changed:false with the reason (same capture, identical content digest, or identical text), never an empty diff. A date with no capture within max_gap_days (default 30) answers status "no_capture", naming which side is missing and the nearest captures to it. Typical uses: how a privacy policy, terms of service, pricing or product page changed; whether a statement was on a page at a given time. Input parameters: - `date_a` (string, required): The earlier date, as YYYY-MM-DD (e.g. "2021-06-01"). - `date_b` (string, required): The later date, as YYYY-MM-DD (e.g. "2024-06-01"). - `max_gap_days` (number): Furthest a capture may be from each date and still be used, in days. Default 30, max 3650. - `url` (string, required): The page address, e.g. "https://www.ftc.gov/policy-notices/privacy-policy". ### `research_row` (~654 tokens) Research Row Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking… Input parameters: - `entity` (object, required): The row/company to research. At least one of name/domain required. - `max_cost` (number): Cost ceiling in US dollars for this one row. Default 0.02, max 0.50, minimum viable 0.002 (below that the call is refused rather than silently exceeding it). - `output_schema` (object, required): JSON Schema object naming the fields to extract, e.g. {"properties":{"sells_to_healthcare":{"type":"boolean"},"head_of_sales":{"type":"string"}}}. Up to 20 fields. - `question` (string, required): The question to answer about this company, in natural language, e.g. "Does this company sell to healthcare, and who is the head of sales?" - `sources` (string): Where to look: "web" (company site only), "catalog" (entity_profile only), "both" (default). ### `classify_row` (~230 tokens) Classify Row Cheap categorization: given a company and a list of candidate labels, decide which labels apply — the most common GTM/AI usage shape (tagging a list by industry, ICP fit, etc.), one small model call. Same evidence contract as research_row: each label comes back {label, applies, evidence_url, quote, status: found|inferred|not_established} — "found" only when the model's quote is independently verified as a verbatim substring of the text used. Pass text directly (cheapest — no fetch) or entity.domain to fetch the homepage once as a fallback. No text and no domain means every label is not_established with no model call made. Input parameters: - `entity` (object, required): The row/company to classify. At least one of name/domain required. - `labels` (array, required): Candidate labels to test, 2-30 strings, e.g. ["healthcare","fintech","logistics"]. - `text` (string): Text to classify directly (a description, a page you already fetched, etc.) — cheapest path, skips any fetch. ### `pipeworx_trending` (~173 tokens) Pipeworx Trending What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window. Input parameters: - `window` (string): 24h (default) | 7d | 30d. Shorter windows surface what's hot right now; longer windows show steady-state demand. ### `suggest_questions` (~240 tokens) What Can I Ask Pipeworx? What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.). Input parameters: - `topic` (string): Optional focus area: finance | pharma | economics | real-estate | betting | weather | government | science | news. Omit for a cross-category spread. ### `generate_llms_txt` (~164 tokens) Generate llms.txt Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor. Input parameters: - `max_links` (number): Maximum number of link entries to include (default 25, max 50). - `url` (string, required): Full URL of the site to summarize, e.g. "https://example.com" or a specific landing page. ### `ai_visibility_check` (~269 tokens) AI Visibility Check Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model is Workers AI Llama-3.3-70b (free); pass `_apiKey` to also probe Anthropic (BYO key — you pay Anthropic directly for those calls). Returns per-model {score, confidence, signals, raw_response} + a combined view. Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring. Input parameters: - `_apiKey` (string): Optional Anthropic API key (sk-ant-...) — only needed if "anthropic" is in models. Passed straight through to api.anthropic.com. - `context` (string): Optional: a phrase locating the entity (e.g. "Boston restaurant", "B2B SaaS"). Helps disambiguate common names. - `entity` (string, required): The thing to ask about. Brand/business name, product name, person, or topic. E.g. "Pipeworx", "OpenInvoice", "Acme Corp pricing". - `models` (array): Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai. ### `scan_competitor_ai_presence` (~225 tokens) Scan Competitor AI Presence Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks by score, surfaces which is most/least recognized. Useful for competitive AI-marketing audits: "does Claude know about us as well as our competitors?". Returns ranked list with score, confidence, signal density per entity. Input parameters: - `_apiKey` (string): Optional Anthropic API key — only if "anthropic" is in models. Passed to api.anthropic.com per probe. - `context` (string): Optional shared context applied to every probe (e.g. "B2B SaaS", "Boston restaurant"). Disambiguates common names. - `entities` (array, required): Array of 2-8 entities to compare (brand/business/product names). First entry treated as the "subject" for narrative; rest are competitors. - `models` (array): Which models to probe. Supported: "workers-ai" (free default), "anthropic" (requires _apiKey). Omit for just workers-ai. ### `pipeworx_feedback` (~383 tokens) Send Pipeworx Feedback Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota. Input parameters: - `claim_token` (string): Read the reply to a report you filed earlier: pass the `pwfb_…` token that filing returned, with no other arguments. Returns the status and, once resolved, what actually changed. - `context` (object): Optional structured context: which tool, pack, or vertical this relates to. - `message` (string): Your feedback in plain text. Be specific (which tool, what error, what data was missing). 1-2 sentences typical, 2000 chars max. - `type` (string): bug = something broke or returned wrong data. feature = a new tool or capability you wish existed. data_gap = data Pipeworx does not currently expose. praise = positive note. other = anything else. ### `remember` (~245 tokens) Remember Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete. Input parameters: - `content` (string): Alias for value. - `data` (string): Alias for value. - `k` (string): Alias for key. - `key` (string, required): Memory key (e.g., "subject_property", "target_ticker", "user_preference"). Accepts name, k, label as aliases. - `label` (string): Alias for key. - `name` (string): Alias for key. - `text` (string): Alias for value. - `v` (string): Alias for value. - `value` (string, required): Value to store (any text — findings, addresses, preferences, notes). Accepts content, text, data, v as aliases; a non-string value is stored as JSON. ### `recall` (~141 tokens) Recall Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete. Input parameters: - `k` (string): Alias for key. - `key` (string): Memory key to retrieve (omit to list all keys). Accepts name, k, label as aliases. - `label` (string): Alias for key. - `name` (string): Alias for key. ### `forget` (~95 tokens) Forget Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall. Input parameters: - `k` (string): Alias for key. - `key` (string, required): Memory key to delete. Accepts name, k, label as aliases. - `label` (string): Alias for key. - `name` (string): Alias for key. ### `pubtator_find_entity` (~240 tokens) Pubtator Find Entity Resolve a gene, disease, chemical/drug, variant, species or cell-line name to its normalized PubTator 3 entity id (e.g. "BRCA1" -> @GENE_BRCA1, NCBI Gene 672; "breast cancer" -> @DISEASE_Breast_Neoplasms, MeSH D001943). Use the id with pubtator_search and pubtator_relations. Sourced from the PubTator 3 autocomplete index at NCBI/NLM, which normalizes to NCBI Gene, MeSH, LitVar/dbSNP and NCBI Taxonomy. Keyless. Input parameters: - `concept` (string): Restrict to one entity type. Omit to search all six. gene, disease, chemical and variant are densely covered; species and cellline autocomplete is sparse. - `limit` (number): Max matches to return, 1-25 (default 10). - `query` (string, required): Name or synonym to look up, e.g. "BRCA1", "metformin", "breast cancer", "V600E". ### `pubtator_search` (~266 tokens) Pubtator Search Search PubMed/PMC literature by biomedical entity and get back, for each paper, the sentence that matched with its entity mentions decoded (gene, disease, chemical, variant, species, cell line — each normalized to an id). Query by plain text ("metformin alzheimer"), by PubTator entity ids combined with AND/OR ("@GENE_BRCA1 AND @DISEASE_Breast_Neoplasms"), or by a relation ("relations:treat|@CHEMICAL_Doxorubicin|@DISEASE_Breast_Neoplasms"). 10 results per page; total count and page count returned. Sourced from the PubTator 3 search index at NCBI/NLM (~36M PubMed abstracts + PMC open-access full text). Keyless. Input parameters: - `page` (number): Result page, 1-based (default 1). 10 results per page. - `query` (string, required): Free text, or PubTator entity ids joined with AND / OR (e.g. "@GENE_BRCA1 AND @DISEASE_Breast_Neoplasms"), or a relation query "relations:||". Get ids from pubtator_find_entit… ### `pubtator_relations` (~352 tokens) Pubtator Relations List the relations PubTator 3 has extracted for a gene, disease, chemical or variant — which drugs treat a disease, which genes a disease is associated with, which chemicals inhibit a gene — ranked by supporting-publication count, each labelled machine-extracted, and the top relations carrying their supporting passages (the actual sentences, with PMIDs). Filter by relation type (treat, cause, associate, interact, inhibit, stimulate, prevent, positive/negative_correlate, cotreat, drug_interact, compare) and/or by a second entity. Accepts a PubTator id (@GENE_BRCA1) or a plain name. Sourced from the PubTator 3 relation-extraction model at NCBI/NLM — predictions from text, not curated. Keyless. Input parameters: - `entity` (string, required): The entity to list relations for: a PubTator id ("@GENE_BRCA1", "@CHEMICAL_Doxorubicin") or a plain name ("BRCA1", "doxorubicin") — a name is resolved via autocomplete and reported in resolved_from. - `evidence_for` (number): How many of the top relations get supporting passages attached (one search each), 0-5 (default 3). Each attaches up to 3 passages with PMIDs. - `limit` (number): Max relations to return, 1-50 (default 20). - `target` (string): Optional second entity to restrict to (id or plain name), e.g. "@DISEASE_Breast_Neoplasms". - `type` (string): Restrict to one relation type. Omit for all types. ### `pubtator_relation_evidence` (~235 tokens) Pubtator Relation Evidence The supporting passages behind one specific PubTator 3 relation — every paper whose text the model read the relation from, with the matched sentence, both entities' mentions, PMID, journal and date. Give the relation type and both entities (ids or plain names); page through the results 10 at a time. Use after pubtator_relations to audit a predicted relation. Sourced from the PubTator 3 search index at NCBI/NLM; the relation itself is machine-extracted, not curated. Keyless. Input parameters: - `entity1` (string, required): First entity — PubTator id or plain name, e.g. "@CHEMICAL_Doxorubicin". - `entity2` (string, required): Second entity — PubTator id or plain name, e.g. "@DISEASE_Breast_Neoplasms". Order does not matter. - `page` (number): Result page, 1-based (default 1). 10 passages per page. - `type` (string, required): Relation type, e.g. "treat", "associate", "inhibit". ### `pubtator_annotations` (~193 tokens) Pubtator Annotations Entity annotations for specific PubMed articles: every gene, disease, chemical, variant, species and cell-line mention in the title and abstract (or PMC full text), each normalized to NCBI Gene / MeSH / dbSNP / Taxonomy ids with its character offsets, plus any relations PubTator 3 extracted within the article. Up to 20 PMIDs per call. Sourced from the PubTator 3 BioC JSON export at NCBI/NLM; all annotations are machine-extracted. Keyless. Input parameters: - `full_text` (boolean): Return PMC open-access full-text passages when available (default false: title + abstract only). Full text can be 100+ passages; each passage is truncated to 1,500 characters. - `pmids` (array, required): PubMed ids, 1-20, e.g. ["31022191", "25616998"]. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp#diagnostics ## Score history - 2026-10-18: 62 - 2026-10-17: 62 - 2026-10-16: 61 - 2026-10-15: 61 - 2026-10-14: 60 - 2026-10-13: 60 - 2026-10-12: 30 - 2026-10-11: 73 - 2026-10-10: 30 ## Common questions ### What is the Pubtator MCP server? Pubtator is an MCP server listed in the public MCP registry as io.github.pipeworx-io/pubtator. PubTator 3 MCP, biomedical entity search, literature search with entity. This page covers its hosted endpoint (https://gateway.pipeworx.io/pubtator/mcp). ### Is the Pubtator MCP server safe to use? Pubtator scores 62 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 Pubtator MCP server expose? Pubtator exposes 46 tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, search_within, deep_research, and 41 more. Their descriptions and schemas cost roughly 21,194 tokens of context every time the server is loaded. ### Does the Pubtator MCP server require authentication? No. We connected to Pubtator without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the Pubtator MCP server still maintained? Pubtator 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. ## Links - Remote endpoint: https://gateway.pipeworx.io/pubtator/mcp - Repository: https://github.com/pipeworx-io/mcp-pubtator - Website: https://pipeworx.io/packs/pubtator - Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp.json - HTML version of this page: https://verifymcp.io/servers/pipeworx-io-pubtator/pubtator-mcp