Submit Log in

Pipeworx

by Pipeworx

Repository Docs

Databases & Data

datagatewaycitationsresearchpublic-datafinance

Summary

Open MCP gateway giving agents live, citable data from 1,300+ verified sources like SEC, FDA, USPTO, and FRED.

Features

5,000+ tools across 1,300+ verified data sources via one connection
Responses carry source metadata and stable citation URIs
On-demand tool loading keeps agent context small
Natural-language ask_pipeworx entry point
Free tier: 50 calls/day anonymous, 200/day with GitHub

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it.
Restart the agent — the "Pipeworx" tools will be available.

{
  "mcpServers": {
    "pipeworx": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://gateway.pipeworx.io/mcp"
      ]
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add pipeworx -- npx -y mcp-remote https://gateway.pipeworx.io/mcp

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "pipeworx": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://gateway.pipeworx.io/mcp"
      ]
    }
  }
}

Native HTTP MCP endpoint for clients with direct HTTP support.

{
  "command": "https://gateway.pipeworx.io/mcp",
  "args": []
}

Description

Pipeworx is an MCP gateway that puts thousands of verified public data sources behind a single MCP connection. Rather than wiring up one server per source, an agent connects once and reaches SEC filings, FDA records, ClinicalTrials.gov, USPTO patents, EPA data, FRED economic series, and more than 1,300 others.

The design detail that matters for research work is citation: every response carries source metadata and a stable citation URI, so a claim an agent makes can be traced back to the record it came from instead of being asserted from memory. Tools are loaded on demand rather than all at once, which keeps the tool list from overwhelming an agent's context, and a natural-language ask_pipeworx entry point lets an agent describe what it needs instead of picking a tool by hand.

It is free to use anonymously at 50 calls per day, rising to 200 per day with a GitHub account. Paid metered plans remove the cap and add premium verticals.

Related MCP Servers

MCP: deja-vu

by Vladislav Shulcz

New

Indexes the coding-agent sessions already sitting on your disk — months of history from before you installed it — and serves them back over MCP. 3.5 GB searched in ~1.5 ms, no LLM, no embeddings.

Developer ToolsDatabases & Data

MCP: Weaviate MCP Server

by Weaviate

New

Weaviate's MCP server, built into the database itself — hybrid search, schema inspection, tenant listing and batch upserts at /v1/mcp, scoped by RBAC.

Databases & Data

MCP: MCP Toolbox for Databases

by Google

New

Google's open-source MCP server for enterprise databases — one binary that fronts AlloyDB, BigQuery, Spanner, Postgres, MySQL, Oracle, MongoDB, Snowflake and more.

Databases & DataCloud & Infrastructure

MCP: DBHub

by Bytebase

Featured

A universal database MCP server — one integration for PostgreSQL, MySQL, SQL Server, SQLite, and MariaDB.

Databases & Data

Browse all MCP servers →