INDIVIDUAL MCP TOOL

search_flights

Search the Epstein flight index — 15,000+ documented flights cross-referenced across ~20 source types (CBP records, court manifests, pilot logbooks, scheduling emails, itineraries).

epstein-data.comnone authenticationAvailability not checked

Input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent endpoint

epstein-data.com

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.epstein-files]
url = "https://epstein-data.com/corpus/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "epstein-files": {
      "type": "http",
      "url": "https://epstein-data.com/corpus/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: epstein-files
Remote MCP URL: https://epstein-data.com/corpus/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "epstein-files": {
      "url": "https://epstein-data.com/corpus/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "epstein-files": {
      "type": "http",
      "url": "https://epstein-data.com/corpus/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "epstein-files",
  "transport": "streamable-http",
  "url": "https://epstein-data.com/corpus/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

search_documents — Search the full text of 2.77M pages across 1.38M Epstein documents.
get_document — Get the full text of a specific document by its EFTA/Bates number.
get_document_metadata — Get metadata for a document: original filename, author, custodian, email headers, dates.
search_images — Search AI-generated descriptions of 92K images extracted from documents.
search_entities — Search the knowledge graph of 524 entities (people, organizations, properties, aircraft).
search_transcripts — Search audio/video transcriptions (190K words from 435 media files).
count_documents — Count documents in the corpus, optionally filtered by a search query.
semantic_search — Semantic search using AI embeddings — understands meaning, not just keywords.