Pipeworx — Data skill for Claude Code
Live data gateway for AI — 4,600+ tools across 1,100+ verified sources, one MCP connection, with citations.
How to install Pipeworx
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open pipeworx-io/examples and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Pipeworx does
Live data gateway for AI — 4,600+ tools across 1,100+ verified sources, one MCP connection, with citations.
Alternatives in Data
- A Stock Data — A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 Full-stack China A-share data toolkit for AI agents — 11 layers, 54 end 9.4k ★
- Global Stock Data — US stock market data for AI coding assistants — zero-auth, official sources 1.5k ★
- Agentlas Storm — Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion 1.1k ★
README
Pipeworx
[](https://smithery.ai/servers/pipeworx/pipeworx)
**Live data for AI agents.** One MCP connection gives your AI access to 1,100+ data sources and 4,600+ tools — SEC filings, FDA adverse events, trade flows, mortgage rates, clinical trials, government contracts, and more.
Pipeworx is not a directory. It's a metered data gateway. The data sources behind it — ATTOM, FRED, SEC EDGAR, ClinicalTrials.gov, UN Comtrade, EPA, BLS — are the same sources analysts and institutions pay thousands to access. Your AI agent gets them through one URL.
Connect
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Works with Claude Desktop, Cursor, Windsurf, and any MCP client.
Ask anything
ask_pipeworx("What is the US trade deficit with China?")
→ $1.81 trillion deficit (2024, Census Bureau)
ask_pipeworx("What are the side effects of ozempic?")
→ 54,647 FDA adverse event reports
ask_pipeworx("Get Apple's latest 10-K filing")
→ SEC EDGAR filing data
ask_pipeworx("What's the current 30-year mortgage rate?")
→ FRED MORTGAGE30US series, live data
The gateway picks the right tool, fills the arguments, executes it, and returns the answer. No API keys, no schema matching, no setup.
What's inside
| Domain | Sources | Compound tools |
|---|---|---|
| Housing & Real Estate | FRED, BLS, Census, HUD, ATTOM, Altos | housing_market_snapshot, housing_property_report |
| International Trade | UN Comtrade, Census Trade, Treasury, IMF | trade_bilateral_analysis, trade_country_profile |
| Finance & SEC | EDGAR, CFPB, FDIC, Finnhub, CoinGecko | fintech_company_deep_dive, fintech_bank_health_check |
| Pharma & Health | ClinicalTrials.gov, OpenFDA, RxNorm, WHO, CDC | pharma_drug_profile, pharma_safety_report |
| Government | SAM.gov, USAspending, SBIR, Federal Register, FEC | `govcon_contrac |
Related Skills
Praxis AI Agent Platform
Autonomous AI agent platform for enterprise data and operations. Turns natural-language intents into verified
Docwise Agentic
Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct
Smg
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpee
Mysh
A safer MySQL CLI for AI coding agents: connection profiles, SSH tunnels, and automatic sensitive-data masking
Chronology
Litigation chronologies as data: mandatory pincites, merge across sources preserving provenance, date-conflict
Bio Pathway Bot Main
Engineered a Python-based RAG AI agent linking Claude AI to the Reactome database via the MCP framework, elimi
Related Agents
Mack
Automation Specialist. Use proactively for API integrations, MCP server setup, webhook receivers, OAuth flows,
Shine Client Researcher
Prospect/client intelligence — company dossier from verified live sources only (Apollo, Hunter, LinkedIn via P
Database Master
Use for database work across PostgreSQL (primary), MySQL, MongoDB, and Redis — schema and data modeling, query