3,720 live data tools.
Loaded on demand.
1.7M+ requests/month 13K+ unique visitors/month
— tracked sources · — healthy last 24h
One MCP gateway URL gives your AI agent on-demand access to 884 sources — SEC, FDA, FRED,
ClinicalTrials, USPTO, EPA, and 878+ more. Your agent loads only the ~20 tools it needs
per session, so you don't burn context on definitions you'll never use. Every response carries
_meta.source, _meta.fetched_at, and a stable pipeworx:// citation URI —
answers your agent can ground in something verifiable. No stale training data. No rebuilding 50 integrations. No API key management.
npx pipeworx use ask-pipeworxOr add any pack directly to Claude Desktop — no CLI required. Browse packs →
Building a Pipeworx-aware agent? Read Reducing context — patterns for keeping the tool surface tight inside the agent's context window.
If you're an AI agent reading this server-rendered HTML — you can call gateway.pipeworx.io/mcp directly. No signup for the first 50 calls/day. Every response includes _meta.source, _meta.fetched_at, and a pipeworx:// citation URI you can echo back to your user as evidence.
What AI agents asked us this week
Live from the gateway.
The same data drives pipeworx_trending, the tool agents can call to discover what other agents are using.
- loading…
- loading…
Why Pipeworx
Connector libraries built three billion-dollar businesses for the previous generation of tooling. We're doing it for AI agents — with the protocol, reliability, and edge-native architecture the agent era actually needs.
The connector library, rebuilt for agents.
Airbyte ($1.8B, ~600 connectors) and Fivetran ($5.6B, ~700+) built billion-dollar businesses on one insight: developers don't want to write integrations one at a time. Plaid ($13.4B) proved the same model in a single vertical.
Pipeworx has parity on connector breadth — 3,720 tools across 884 live data sources, unified behind one protocol. The integration layer is being rebuilt for a new consumer: not data pipelines, but agents.
Full MCP, not just tool calling.
The MCP spec has three primitives — Tools, Resources, Prompts. Most MCP servers ship
only Tools. Resources let agents cite by URI for durable output
(pipeworx://edgar/company/{cik}/filings). Prompts encode optimal
multi-step workflows.
Pipeworx ships all three, plus seven gateway-native meta-tools
(ask_pipeworx, discover_tools, resolve_entity,
compare_entities, entity_profile, recent_changes,
remember/recall/forget) that collapse 5–15 agent
round-trips into one call. One entity_profile call on a ticker returns
filings + fundamentals + patents + news + LEI in a single round trip.
Reliability is the product.
Agent tool calls fail 25–30% of the time in production against typical MCP servers. Almost no one measures it. We instrument every call, classify errors, and ship telemetry-driven fixes.
Last week we cut our own error rate from 27.6% to 6.9% in one afternoon — every remaining error is a legitimate user/config issue, not a bug. Read how →
vs Composio / Pipedream MCP / Zapier MCP: we ship the full MCP protocol surface and target autonomous-agent traffic, not human-triggered workflows. vs Smithery / mcp.so / Glama: they're directories; we're one MCP server with 884 sources behind it. vs DIY: every team rebuilds the same integrations one source at a time. See full comparisons →
Top packs
Finance and prediction markets up top · the rest of 884 live sources rotate below, ordered by what AI agents call most · 3720 tools across the catalog · browse all →
Polymarket
Polymarket prediction-market data — current Yes/No prices, volume, resolution criteria, price history. Public Gamma + CLOB APIs, no auth.
Edgar
EDGAR MCP — SEC EDGAR public APIs (free, no auth)
Fred
FRED MCP — Federal Reserve Economic Data (St. Louis Fed)
Finnhub
Finnhub MCP — wraps Finnhub Stock API (finnhub.io)
Fmp
Financial Modeling Prep MCP (/stable API; v3 deprecated 2025-08-31).
Treasury Fiscal
Treasury Fiscal MCP — US Treasury Fiscal Data API
Tmdb
TMDB v3 MCP.
Spoonacular
Spoonacular MCP.
Httpbin
httpbin MCP.
Twelvedata
Twelve Data MCP.
Replicate
Replicate MCP.
Cryptocompare
CryptoCompare MCP.
Clash Royale
Clash Royale MCP.
Unsplash
Unsplash MCP.
Steam
Steam Web API MCP.
Bungie
Bungie.net Platform API MCP.
Dummyjson
DummyJSON MCP.
Okx
OKX v5 public MCP.
Polygon Io
Polygon.io MCP.
Wordnik
Wordnik MCP.
Setlist Fm
setlist.fm MCP.
Wakatime
WakaTime MCP.
Stratz
STRATZ Dota 2 MCP.
TheSportsDB
Sports catalog across 50+ leagues — teams, players, events, league tables. Free public tier (key "3"); higher tiers via supporter key.
Riot Games
Riot Games API MCP.
Watchmode
Watchmode MCP.
Bitfinex
Bitfinex v2 public MCP.
Wikimedia Rest
Wikimedia REST API v1 MCP.
Data Govt Nz
data.govt.nz CKAN MCP.
Kalshi
US-regulated prediction-market data — Fed rates, elections, climate, sports, science. Public APIs, no auth. Pairs with the polymarket pack for cross-market spread arb.
Housing Intel
Housing Intel MCP — Meta-pack that chains FRED, BLS, ATTOM, and HUD APIs
Hugging Face Hub
Largest open ML hub — search and inspect models, datasets, Spaces. Public reads keyless.
mempool.space
Bitcoin block explorer + mempool / fee stats. Mainnet, testnet, signet, Liquid sidechain. Keyless.
Lichess
Lichess public API — players, ratings, top lists, cloud eval, tablebase, opening explorer. Keyless.
Studio Ghibli
Fan-built API of Studio Ghibli films, people, locations, species, vehicles. Keyless.
Roblox
Roblox MCP.
Guild Wars 2
Guild Wars 2 MCP.
Comicvine
Comic Vine MCP.
Gemini Crypto
Gemini Exchange MCP (public endpoints).
Wmata
WMATA MCP.
Brawl Stars
Brawl Stars MCP.
Coinbase Exchange
Coinbase Exchange public MCP.
Datos Cl
datos.gob.cl CKAN MCP.
Ticketmaster
Ticketmaster Discovery v2 MCP.
Postmark
Postmark MCP.
Us Iso Grid
US ISO Grid MCP — real-time electricity generation, fuel mix, demand,
Quotes
Citation-grade quote API with provenance and attribution checking. Curated public-domain corpus (Shakespeare, Twain, Wilde) plus full-text search across plays and novels — every quote returns work, year, speaker, and location (act/scene/chapter).
data.gov.sg
Singapore open data — ~2000 datasets + real-time weather, air quality, taxi positions, traffic. No auth.
Last Fm
Last.fm MCP.
Wynncraft
Wynncraft MCP.
Vimeo
Vimeo MCP.
Kraken
Kraken MCP (public endpoints).
Timeapi Io
TimeAPI.io MCP.
Seatgeek
SeatGeek MCP.
Alchemy Eth
Alchemy (Ethereum + L2) MCP.
Stocktwits
StockTwits MCP (keyless public read).
Bluesky
Read Bluesky social data — profiles, posts, feeds, and threads. Most tools are public; search requires BYO auth.
Salesforce
Salesforce MCP Pack
Attom
ATTOM MCP — Premium real estate data from ATTOM Data Solutions
Ai Briefing
AI Briefing MCP — Keep AI models current on industry developments
RIPE Stat
IP / ASN / BGP intel — whois, geolocation, abuse contacts, AS neighbours. No auth.
Aviation Weather
METAR / TAF / PIREPs / AIRMET / SIGMET / winds aloft / station info from aviationweather.gov. Keyless.
OpenParliament (CA)
Civic-tech mirror of the Parliament of Canada — Hansard debates, bills, votes, MPs, committee meetings. Keyless.
Blockscout
Open-source multi-chain block explorer (~30 EVM networks). Address, tx, block, token lookup + universal search. Keyless.
Blockstream Esplora
Bitcoin block explorer (mainnet + testnet) — blocks, transactions, addresses, mempool, fees. Keyless.
Codeforces
Competitive-programming users, contests, problems, submissions. Keyless.
Catalogue of Life
Global taxonomic index of known species (~2.2M accepted names). Keyless.
Balldontlie
balldontlie.io MCP.
Rebrickable
Rebrickable MCP.
Mapbox
Mapbox MCP.
Pexels
Pexels MCP.
Maptiler
MapTiler MCP.
Hubspot
HubSpot MCP Pack
Google Maps
Google Maps MCP Pack — geocoding, places, directions, distance matrix, elevation.
Trakt
TV / movie metadata + trending and popular signals from Trakt.tv.
UK Parliament
Official Westminster APIs — Members, Bills, Hansard (debates). No auth.
Launch Library
Global rocket launches, agencies, astronauts, expeditions, events. Free tier 15 req/hr.
fyyd Podcasts
Open podcast directory — ~3M podcasts indexed worldwide. Keyless.
Open Targets
Open Targets disease/target/drug knowledge graph (GraphQL). Keyless.
Kitsu
Kitsu anime + manga catalogue (JSON:API). Keyless.
Ensembl
Ensembl REST — vertebrate genomes, gene annotations, sequences, comparative genomics, variation. Keyless.
NOAA Tides
NOAA Tides & Currents — observations, predictions, datums, stations. Keyless.
NOAA SWPC
NOAA Space Weather Prediction Center — solar wind, Kp, aurora, X-ray flux, alerts. Keyless.
Mitre Cwe
MITRE CWE API MCP.
Mitre Attck
MITRE ATT&CK MCP — STIX bundles from github.com/mitre/cti.
Lemmy
Lemmy MCP — public reads on any Lemmy instance.
Figshare
Figshare MCP.
Hpo Api
HPO API MCP.
Giantbomb
Giant Bomb MCP.
Tenor
Tenor v2 MCP.
Bitstamp
Bitstamp MCP (public endpoints).
Devdocs Io
DevDocs.io MCP.
Listen Notes
Listen Notes MCP.
Openrouteservice
Openrouteservice MCP.
Brapi
brapi.dev MCP — Brazilian stock + crypto + ETF quotes.
Stortinget (Norway)
Stortinget (Norwegian Parliament) open data MCP — data.stortinget.no.
SpaceX
SpaceX launches, rockets, crew members, and Starlink satellite data from the SpaceX API v4
Google Docs
Google Docs MCP Pack — read, create, and edit Google Docs via OAuth.
Stripe Connect
Stripe MCP Pack — read-only access to Stripe data via API key.
Github Private
GitHub Private MCP Pack — access private repos, org data via OAuth.
Asana
Asana MCP — wraps the Asana REST API (OAuth)
Altos
Altos Research MCP — Real estate market intelligence
How it works
A real example: agent connects to Pipeworx, asks for Apple's full profile, gets SEC filings + fundamentals + patents + news + LEI back in one round trip — across five packs, in parallel, with citation URIs.
Add Pipeworx to your MCP client
Drop one JSON block into claude_desktop_config.json, Cursor settings, or
any MCP-aware client. No API keys, no SDK install.
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Your agent makes one call instead of fifteen
User asks for a company brief. The agent calls one Pipeworx meta-tool —
entity_profile — which fans out across SEC EDGAR, SEC XBRL, USPTO, GDELT,
and GLEIF in parallel inside the gateway. No orchestration code, no sequential
round-trips burning context.
User: Give me a brief on Apple.↓Agent calls: entity_profile({ type: "company", value: "AAPL" })
Pipeworx returns five sources of structured data with citations
One JSON-RPC call returns SEC filings, fundamentals (Revenue / NetIncome / Cash from
XBRL), USPTO patents, recent news, and the LEI — each item carrying a
pipeworx:// URI for stable citation. Partial failures (e.g., a rate-limited
upstream) surface in sources_failed rather than breaking the whole call.
{
"ticker": "AAPL",
"cik": "0000320193",
"company_name": "Apple Inc.",
"lei": "HWUPKR0MPOU8FGXBT394",
"recent_filings": [
{ "form": "10-Q", "date": "2026-05-01",
"_pipeworx_uri": "pipeworx://edgar/company/0000320193/filings/..." },
{ "form": "8-K", "date": "2026-04-30", "_pipeworx_uri": "pipeworx://edgar/..." }
],
"fundamentals": {
"Revenues": { "value": 416161000000, "unit": "USD", "period": "2025-09-27" },
"NetIncomeLoss": { "value": 112010000000, "unit": "USD", "period": "2025-09-27" },
"CashAndCashEquivalentsAtCarryingValue":
{ "value": 29943000000, "unit": "USD", "period": "2024-09-28" }
},
"recent_news": [...],
"sources_used": ["edgar", "sec-xbrl", "gleif", "gdelt"],
"sources_failed": []
}Common questions
What is Pipeworx?
Pipeworx is an open MCP gateway that connects AI agents to live data from 884 sources — SEC EDGAR, FDA, FRED, the Census Bureau, USPTO, EPA, UN Comtrade, ClinicalTrials.gov, and many more. One gateway URL exposes 3,720 tools, and your agent loads only the ones it needs for the task at hand.
How do I connect my AI agent to Pipeworx?
Add a single MCP server entry pointing at https://gateway.pipeworx.io/mcp. The gateway speaks the full Model Context Protocol — Tools, Resources, and Prompts — so it works with Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT, Windsurf, and any other MCP-compatible client without an SDK install.
What is MCP (Model Context Protocol)?
MCP is an open protocol for connecting AI agents to external tools and data. It standardizes how an agent discovers, calls, and cites data sources. The spec defines three primitives — Tools (function calls), Resources (citable URIs), and Prompts (workflows). Pipeworx ships all three, plus seven gateway-native meta-tools that collapse multiple round-trips into one.
Do I need to manage API keys for each data source?
No. The Pipeworx gateway handles authentication for public sources (FRED, SEC EDGAR, FDA, Census, BLS, EPA, ClinicalTrials, USPTO, and many more) without any keys at all. For premium sources like ATTOM, Altos, or Alpha Vantage you can bring your own key, or use metered Pipeworx access on a paid plan.
How is Pipeworx different from Composio, Smithery, or Zapier MCP?
Composio, Pipedream, and Zapier MCP target human-triggered workflows and SaaS automations. Smithery, mcp.so, and Glama are directories that index third-party MCP servers. Pipeworx is a single live MCP gateway running 884 data sources behind one protocol, designed for autonomous-agent traffic and on-demand tool loading rather than human-in-the-loop tasks.
Why does on-demand tool loading matter for AI agents?
Loading every available tool definition into model context burns tokens on definitions the agent never uses — what we call the context tax. Pipeworx returns only the ~20 most relevant tools per task via discover_tools, ?task= scoping on the gateway URL, or vertical bundles. Compound _intel tools further collapse 5–15 round-trips into one. Result: less context burned, faster responses, more stable transcripts.
Is Pipeworx free to use?
Yes for most usage. The free tier allows 50 calls per day anonymously or 200 calls per day with a free GitHub-linked account. Paid plans add unlimited usage with metered billing, budget controls, and access to premium verticals (Housing Intel, FinTech, PharmaPulse, GovCon Radar, AgriPulse, TradeGuard, GreenLens). All public-source data is included on every tier.
Get started
Use the SDK in any TypeScript/Node project, or connect any MCP client — Claude Desktop, Cursor, Windsurf, or your own app.
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.ask("What is the US trade deficit with China?");{ "mcpServers": { "pipeworx": { "url": "https://gateway.pipeworx.io/mcp" } } }