Live data your agents run on.
5,929 live data tools behind one URL.
Frontier models: 100% correct with Pipeworx, 63% with web search
1.7M+ requests/month 13K+ unique visitors/month
— tracked sources · — healthy last 24h
Augment the systems you already have. A retrieval index, an enrichment job, a nightly report — each one was accurate when it was built, and each one drifts. Pipeworx is the live half: 1,544 primary sources behind one URL, including the SEC, the FDA, the Fed, ClinicalTrials, USPTO and EPA. Every answer carries its source and fetch time, so what your system writes down stays checkable. No API keys, and your agent loads only the ~20 tools a job needs.
Watch EU tenders in the categories you bid on. Flag the drugs clearing Phase 2 in your therapeutic area. Track a competitor’s patent filings. Jobs that run on a schedule, not questions you type once.
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 — 5,929 tools across 1,544 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.
In May 2026 one of those passes took our error rate from 27.6% to 6.9% in an afternoon, and most of what remained turned out to be user or config error rather than a bug of ours. 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 1,544 sources behind it. vs DIY: every team rebuilds the same integrations one source at a time. See full comparisons →
Top packs
The 9 most-used, by how many different agents reached for them this week — not by how many calls they took, which would just show you whoever ran the biggest job. The rest of 1,544 sources rotate below · 5,929 tools across the catalog · browse all →
China Stocks
The Chinese A-share market's LIMIT-UP board (涨停板) for a trading day — how many stocks hit their daily price limit (+10%, or +20% for STAR/ChiNext) and the ranked list of those stocks.
TED (EU procurement)
Tenders Electronic Daily — EU public procurement notices, ~700k/year. Searchable by buyer country, CPV code, value.
GLEIF
Global Legal Entity Identifier Foundation — canonical 20-character LEI lookup and corporate hierarchy for ~2.5M financial-market entities. No auth.
SEC EDGAR
Every filing US public companies make to the SEC — 10-K, 10-Q, 8-K — plus the XBRL financials inside them, by ticker or CIK.
Statcan
Statistics Canada (StatCan) time-series via the Web Data.
Polymarket
Polymarket prediction-market data — current Yes/No prices, volume, resolution criteria, price history. Public Gamma + CLOB APIs, no auth.
FRED
US economic series from the St. Louis Fed — interest rates, inflation, unemployment, GDP — with the release each figure came from.
Patents
Search US patents by keyword, retrieve patent details, and look up inventors via PatentsView
EPO Open Patent Services
European Patent Office worldwide patent register — search, biblio, family, abstracts, claims.
Openfigi
OpenFIGI (Bloomberg) — map tickers, ISINs, CUSIPs, and other identifiers to standardized FIGIs for financial instruments. Keyless.
Sec Xbrl
SEC EDGAR XBRL API — retrieve structured financial facts, track any XBRL metric over time, and get high-level annual financial summaries for public US companies.
deps.dev
Google's package metadata + dependency graph API. Keyless.
Bundlephobia
Bundle-size analysis for npm packages — minified + gzipped, tree-shakeability, dependency count. Keyless.
DEX Screener
Real-time DEX prices and liquidity across all major EVM + Solana chains. Keyless.
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.
Pipeworx Catalog
Pipeworx platform self-index — list, search, and get connection configs for all hosted MCP packs and the broader community MCP directory.
Crypto
Cryptocurrency prices and market data from CoinGecko, plus currency conversion
Ai Briefing
AI Briefing — daily digest of AI model releases, new MCP servers, SDK updates, and industry news from HN, GitHub, and AI company blogs.
GDELT
Global Database of Events, Language, and Tone — 100+ languages, 15-min refresh. Article search, tone timelines, volume timelines. No auth.
Fda Drug Competition
Orange Book competitive intelligence from FDA's monthly official data ZIP.
Crossref
Search and retrieve academic paper metadata — DOIs, authors, citations, and journals via Crossref
GitHub
Search repositories, get repo details, list issues, and look up user profiles via GitHub REST API
Internet Archive
Search the Internet Archive, retrieve item metadata, and check Wayback Machine snapshots
Europe PMC
Europe PubMed Central — biomedical literature search, abstracts, references, citations. Keyless.
Commons Wikimedia
Freely licensed images, audio and video from Wikimedia Commons, with their licence and author.
H1b
US H-1B visa sponsorship & wage data from DOL Labor Condition.
Tatoeba
Tatoeba multilingual sentence corpus (~13M sentences, 400+ languages). Keyless.
Prozorro
Most recently updated tenders from Ukraine's ProZorro national procurement system (via the keyless OpenProcurement public feed).
Stocktwits
StockTwits social feed — real-time investor messages, trending tickers, watchlists, and sparkline chart data (keyless public read).
Weather
Real-time weather conditions and multi-day forecasts from Open-Meteo
The Odds API
Sportsbook odds across 70+ books, 30+ leagues (NFL, NBA, MLB, NHL, soccer, MMA, golf, tennis, esports, cricket). Free tier 500 req/month.
DOL Form 5500
Search employee-benefit & pension filings (EFAST2) by sponsor, EIN, or plan: participant counts, plan assets, filing history, and full filing PDFs. Keyless.
Wikidata
Wikidata — search and retrieve structured entity records (people, places, concepts) with multilingual labels, aliases, and linked claims. No auth.
Statistics Portugal (INE)
Statistics Portugal (INE) — fetch metadata and data values for Portugal's official statistical indicators.
Wikipedia
Search and retrieve Wikipedia articles — summaries, section structure, and random article discovery
Clinicaltrials
Search ClinicalTrials.gov for clinical trials — find trials and look up a NAMED trial by keyword, condition, drug/therapy, status (e.g.
Economic Data
US unemployment rate, CPI inflation, and employment figures from the Bureau of Labor Statistics
Date Calculator
Difference between dates, add/subtract durations (month-end clamped), and calendar facts (weekday, ISO week, quarter, leap year). UTC, keyless, offline.
Semantic Scholar
Search 200M+ academic papers on Semantic Scholar by keyword.
Usaspending
Federal spending data from USAspending.gov API.
Medicare Coverage
Search current Medicare National Coverage Determinations (NCDs) by title, benefit category, or NCD number.
Fmp
Financial Modeling Prep — company profiles, quotes, financial statements, ratios, earnings/IPO calendars, insider trading, and ETF holdings via the stable API.
Tmdb
The Movie Database (TMDB) — search and retrieve movies, TV shows, cast/crew, trailers, and trending content.
Openfda
Search adverse event reports for drugs by name, reaction type, or date range.
Spoonacular
Spoonacular — recipe search, nutrition analysis, meal planning, ingredient details, wine pairings, and grocery products.
Twelvedata
Twelve Data — real-time and historical OHLC, quotes, forex rates, earnings calendars, dividends, and company profiles for stocks/ETFs/crypto/indices.
Okx
OKX v5 public API — tickers, orderbooks, OHLC candles, funding rates, mark prices, and index data for crypto spot/futures/options.
Httpbin
httpbin — HTTP testing service: echo requests, return specific status codes, generate UUIDs, encode/decode Base64, and sample payloads.
Replicate
Replicate API — browse, run, and manage AI model predictions and deployments across thousands of hosted ML models.
CoinDesk Data (formerly CryptoCompare)
CoinDesk Data (formerly CryptoCompare) — multi-exchange crypto prices, OHLC history, market cap rankings, news, social stats, and coin/exchange lists.
Clash Royale
Clash Royale official API — player profiles, clan data, war logs, tournament info, card lists, and leaderboards.
Unsplash
Unsplash — search and retrieve high-resolution free stock photos, user profiles, collections, and editorial topics.
Steam
Steam Web API — player profiles, owned games, achievements, VAC bans, app details, and concurrent player counts.
Hackertarget
HackerTarget — open-source network intelligence tools including DNS lookups, port scans, and OSINT reconnaissance.
Bungie
Bungie.net API — Destiny 2 player profiles, characters, clans, loadouts, historical stats, and manifest definitions.
Dummyjson
DummyJSON — fake REST API returning placeholder products, users, posts, comments, recipes, and todos for testing and prototyping.
PubMed
Search biomedical literature, fetch abstracts, and retrieve article metadata via NCBI PubMed
Massive (formerly Polygon.io)
Massive (formerly Polygon.io) — US stock market data: tickers, OHLC bars, dividends, splits, news, market status, and exchange reference.
Wordnik
Wordnik — English-language dictionary API: definitions, examples, pronunciations, frequency, related words, and word-of-the-day.
Setlist Fm
setlist.fm — concert setlist database: search artists, venues, setlists, and user attendance history for live music events.
Wakatime
WakaTime — retrieve coding activity stats, daily summaries, durations, goals, project commits, and public leaderboards for developers.
Stratz
STRATZ API — Dota 2 hero stats, match history, player profiles, live matches, and tournament data via GraphQL. Requires your own STRATZ API token (_apiKey), free at stratz.com/api.
TheSportsDB
Sports catalog across 50+ leagues — teams, players, events, league tables. Free public tier (key "3"); higher tiers via supporter key.
Roblox
Roblox API — user profiles, friends, badges, games, groups, and presence data from the Roblox gaming platform.
Guild Wars 2
Guild Wars 2 API — items, achievements, professions, WvW matches, and trading-post prices for the GW2 MMO.
Riot Games
Riot Games API — League of Legends player accounts, match history, ranked entries, champion mastery, and rotations.
Bitfinex
Bitfinex v2 public API — tickers, orderbooks, trades, OHLC candles, derivatives status, and liquidations for crypto markets.
Wikimedia Rest
Wikimedia REST API — fetch Wikipedia page summaries, HTML, metadata, media, revisions, on-this-day events, and daily featured content.
Data Govt Nz
data.govt.nz CKAN — search and browse New Zealand government open datasets, organizations, groups, and resources.
Cms Open Payments
CMS Open Payments, with annual dataset discovery through the official DKAN API.
Taiwan Stocks
Taiwan equities MCP. Keyless.
Housing Intel
Housing Intel — meta-pack chaining FRED, BLS, ATTOM, HUD, and Zillow for mortgage rates, property reports, affordability checks, and metro rental screening.
US Case Law
US case law — search court opinions and dockets from the Supreme Court, federal circuit and district courts, and state appellate and supreme courts, plus PACER/RECAP docket archives. The case-law counterpart to the statute packs (us-code for federal statutes, the state code packs for state ones): statutes say what the rule is, these say how courts have applied it. Sourced from CourtListener (Free Law Project), keyless.
MLB Stats API
Official MLB statistics — schedule, scores, rosters, player stats, standings, box scores, live game feed. No auth.
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.
Comicvine
Comic Vine — comic book database: search characters, issues, volumes, creators, and publishers.
Watchmode
Watchmode — streaming availability API: find where movies and TV shows are available to watch across streaming platforms.
Gemini Crypto
Live crypto prices, order books and recent trades from the Gemini exchange. No account needed.
Clinicaltables
NIH Clinical Tables Search Service — autocomplete lookups for medical terms, diagnoses, drugs, and clinical data from NIH.
Wmata
WMATA — real-time Washington DC Metro rail predictions, incidents, bus arrivals, and route information.
Brawl Stars
Brawl Stars official API — player profiles, club data, brawler details, event rotation, and country rankings.
Coinbase Exchange
Coinbase Exchange public API — trading pairs, orderbooks, tickers, recent trades, OHLC candles, and 24h stats for crypto markets.
Datos Cl
datos.gob.cl CKAN — search and browse Chile's government open datasets, organizations, groups, and resources.
Ticketmaster
Ticketmaster Discovery v2 — search live events, venues, and attractions worldwide with ticket availability and classification data.
Postmark
Postmark — send transactional emails, query delivery stats, inspect outbound history, manage bounces, and review server configuration.
Us Iso Grid
Real-time US electricity grid data (CAISO/ERCOT/NYISO): fuel mix, demand, renewables, CO2 intensity, and locational marginal prices.
Fda Devices
FDA medical-device regulatory intelligence from keyless openFDA datasets.
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).
NIH RePORTER
Every NIH-funded research grant — PI, institution, fiscal year, award amount, abstract, mesh terms, congressional district. No auth.
data.gov.sg
Singapore open data — ~2000 datasets + real-time weather, air quality, taxi positions, traffic. No auth.
Last Fm
Last.fm music API — retrieve artist bios, top tracks, similar artists, album/track metadata, user listening history, and global music charts.
Wynncraft
Wynncraft API — player stats, guilds, leaderboards, item database, and server info for the Wynncraft Minecraft MMORPG.
Vimeo
Vimeo API — search and browse videos, user profiles, channels, and categories on the Vimeo video platform.
Kraken
Live crypto prices, order books and recent trades from the Kraken exchange. No account needed.
Timeapi Io
TimeAPI.io — current time by timezone, coordinates, or IP; timezone conversion, zone info, and ISO date parsing.
Seatgeek
SeatGeek — search concerts, sports, and theater events; find venues and performers; get ticket recommendations.
Alchemy Eth
Alchemy — query Ethereum and L2 chains for ERC-20 token balances/metadata, NFT ownership, asset transfer history, and raw JSON-RPC calls.
Dubai Land
Dubai Land Department (DLD) — Dubai real-estate open data.
Bluesky
Read Bluesky social data — profiles, posts, feeds, and threads. Most tools are public; search requires BYO auth.
Salesforce
Query, search, and manage Salesforce CRM records — accounts, contacts, opportunities — via SOQL and SOSL
Attom
Premium real estate data from ATTOM Data Solutions.
RIPE Stat
IP / ASN / BGP intel — whois, geolocation, abuse contacts, AS neighbours. No auth.
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 1544 sources — SEC EDGAR, FDA, FRED, the Census Bureau, USPTO, EPA, UN Comtrade, ClinicalTrials.gov, and many more. One gateway URL exposes 5,929 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 1544 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" } } }