mcpField
E
Epstein Exposed MCP

Epstein Exposed MCP

Local
epsteinexposed-mcp.vercel.appLegal & Government4Updated 11w ago

About Epstein Exposed MCP

An MCP server that exposes the Epstein Exposed public API as tools for AI agents researching publicly released case records. It supports searches across people, documents, flight logs, and emails.

Key features

  1. 01Search people by name and category
  2. 02Retrieve detailed person records
  3. 03Full-text search case documents
  4. 04Search flight logs by passenger and route
  5. 05Search documents and emails together

Use cases

  1. 01Find a person and their public record details
  2. 02Search the contents of case documents
  3. 03Find flight records by passenger, year, or route

MCP support

This MCP server exposes structured search tools backed by the Epstein Exposed public API to MCP clients, communicating over stdio or SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

epsteinexposed-mcp

CI Codacy Badge codecov Python MCP License: MIT

Model Context Protocol server exposing the Epstein Exposed public API as AI-agent tool calls.

Plug directly into any MCP-compatible client (Claude Desktop, Cursor, SmolAgents, etc.) to search persons, documents, flight logs, and emails from the Epstein case files.

epsteinexposed-mcp

Disclaimer: Inclusion in the Epstein Exposed database does not imply guilt or wrongdoing. All data is derived from publicly released government records.

Tools

ToolDescription
search_personsSearch/filter persons of interest by name and category
get_personGet full detail for a person by slug (bio, aliases, stats)
search_documentsFTS5 full-text search across case documents
search_flightsSearch flight logs by passenger, year, origin, destination
cross_searchSearch across documents and emails simultaneously

Quick Start

# Install
pip install -e ".[dev]"

# Run via stdio (for MCP clients)
python -m src.server

# Or via the MCP CLI
mcp run src/server.py

MCP Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "epstein-files": {
      "command": "epsteinexposed-mcp",
      "args": []
    }
  }
}
Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "epstein-files": {
      "command": "epsteinexposed-mcp",
      "args": []
    }
  }
}

Architecture

MCP Client (Claude, Cursor, SmolAgents)
    │
    │  JSON-RPC 2.0 (stdio / SSE)
    ▼
epsteinexposed-mcp (FastMCP)
    │
    │  AsyncEpsteinExposed (curl_cffi)
    ▼
epsteinexposed.com/api/v1

Powered by the epsteinexposed Python package.

Development

git clone https://github.com/releasetheepsteinfiles/epsteinexposed-mcp.git
cd epsteinexposed-mcp
pip install -e ".[dev]"
pytest -v

Documentation

Full docs available at the docs site (VitePress).

The toolchain

This repository is one of four that share a data source and a design system:

RepoRole
epsteinexposedPython client for the public API
epsteinexposed-mcpMCP server — structured search (this repo)
epstein-files-rag-mcpMCP server — semantic search (in development)
epsteinexplorerNatural-language chat app

A 20-second overview of how the four fit together:

Epstein Files toolchain

Design system

All four repositories share the "Declassified" visual language — a dark archival palette with a single ember accent, monospace structure and Inter prose. The canonical tokens live in brand/tokens.css and the rationale in brand/DESIGN.md; both files are byte-identical across the four repos.

The VitePress theme maps --vp-* onto that palette in docs/.vitepress/theme/custom.css.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.