Science Feeds MCP.
Science Feeds MCP.
mcp_partial Not production-safe Score 96/100 http no auth
At a glance
| Endpoint | https://gateway.pipeworx.io/science-feeds/mcp |
|---|---|
| Source | https://github.com/pipeworx-io/mcp-science-feeds |
| Transport | http |
| Tools | 0 |
| Auth | none |
| First seen | 2026-08-26 23:36:14 |
| Last checked | 2026-11-16 19:17:24 |
Observed reliability
| 7-day uptime | 99% |
|---|---|
| 24-hour uptime | — |
| Handshake success | 100% |
| Latency p50 / p95 | 256 / 578 ms |
| Last successful check | 2026-11-16 19:02:24 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (0)
ask_pipeworx— PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, governmentask_pipeworx_beta— Beta version of ask_pipeworx: identical universal router (same 7,498 tools, same arguments, same response shape) with candidate routing imprask_pipeworx_grounded— Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 7,498 across 1989 sourcesearch_within— 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 natudeep_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, usdiscover_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, finaresolve_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 officompare_entities— "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to headsubscribe— Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id. Requires a Pipeworx OAuth account (unsubscribe— Cancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so itslist_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 yorecent_alerts— Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carrieentity_profile— "Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown onrecent_changes— "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "whavalidate_claim— "Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" —company_facts— TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period — "Apple revenue for fiscal 2023", "Wacompany_register_search— Search the NATIONAL BUSINESS REGISTERS by company name and get the register's own id back — a Companies House number, a Norwegian organisasjscan_dependency— Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version historybet_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-repubpolymarket_arbitrage— Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of thpolymarket_edges— Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today"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 apapolymarket_fill_risk— Realizable-vs-theoretical edge check against live CLOB order-book depth — AND Polymarket's own taker fee, which is never zero and is foldedpolymarket_edge_tracker— Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinkinkalshi_weather_edge— Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forresolution_audit— Extract the settlement clause of a single Polymarket (.com or .us) or Kalshi market: who publishes the settling number (source), the clock tresolution_diff— Field-by-field diff of TWO markets' settlement clauses (one from each of `a` and `b`; either can be Polymarket .com, Polymarket US, or Kalshrelease_calendar_markets— JOIN of the official release calendar (econ data, the FOMC, FDA decisions, SEC rules) against LIVE Polymarket/Kalshi markets — which schedulprediction_calibration— REALIZED win rate by shown price and minutes elapsed for short-horizon crypto up/down markets, net of taker fee — read from our own settled-updown_venue_compare— The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is acupdown_divergence_rate— How often two venues settled the SAME 15-minute crypto window differently, over every settled window on record. Compares polymarket.com (Chaarchive_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,archive_compare— What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawresearch_row— Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every fielclassify_row— Cheap categorization: given a company and a list of candidate labels, decide which labels apply — the most common GTM/AI usage shape (tagginpipeworx_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, 7suggest_questions— What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data dogenerate_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 pai_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 iscan_competitor_ai_presence— Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, rankspipeworx_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 wishremember— Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying frecall— Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlforget— 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 escience_feeds_list_feeds— List the curated science & space feeds (id, title, category, source). Optionally filter by category (science) or keyword. Pass an id to readscience_feeds_read_feed— Read a curated science & space feed by its id (from list_feeds). Returns normalized items (title, link, published, summary). Optionally filtscience_feeds_fetch_feed— Fetch and normalize any RSS / Atom / RDF feed by URL. CF-robust: fetches directly and falls back to a proxy if the source blocks the gateway
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-16 19:17:24 | ✓ | ✓ | 269 ms | 56 | mcp_partial |
| 2026-11-16 19:02:24 | ✓ | ✓ | 363 ms | 91 | active |
| 2026-11-16 18:47:23 | ✓ | ✓ | 371 ms | 91 | active |
| 2026-11-16 18:32:22 | ✓ | ✓ | 343 ms | 91 | active |
| 2026-11-16 18:17:21 | ✓ | ✓ | 199 ms | 95 | active |
| 2026-11-16 18:02:21 | ✓ | ✓ | 157 ms | 95 | active |
| 2026-11-16 17:47:04 | ✓ | ✓ | 369 ms | 91 | active |
| 2026-11-16 17:32:03 | ✓ | ✓ | 158 ms | 95 | active |
| 2026-11-16 17:17:02 | ✓ | ✓ | 355 ms | 91 | active |
| 2026-11-16 17:02:00 | ✓ | ✓ | 169 ms | 95 | active |
| 2026-11-16 16:45:43 | ✓ | ✓ | 193 ms | 95 | active |
| 2026-11-16 16:30:40 | ✓ | ✓ | 239 ms | 95 | active |
| 2026-11-16 16:15:39 | ✓ | ✓ | 252 ms | 95 | active |
| 2026-11-16 16:00:37 | ✓ | ✓ | 202 ms | 95 | active |
| 2026-11-16 15:43:17 | ✓ | ✓ | 265 ms | 95 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://gateway.pipeworx.io/science-feeds/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/gateway-pipeworx-io-science-feeds-mcp # JSON