MCP server exposing 4 tools for epstein.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/epstein/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}
epstein_search_documents — Full-text search across the House Oversight Committee documents from the Jeffrey Epstein investigation — transcribed interviews, subpoenas and letters the committee published as PDFs. Returns the matching page with a snippet, the document title and the committee URL, so every result can be checked at source. Use it to find what a named witness said under questioning, which institutions were subpoenaed, or where a topic appears in the record.epstein_list_documents — Inventory of every document held from the House Oversight Epstein investigation: title, kind, page count, publication date and the committee URL. Says which documents are scans with no searchable text. Use it to see what the corpus contains before searching it, or to get a document id for epstein_get_document.epstein_get_document — Read the full text of one document from the House Oversight Epstein investigation, a page at a time, given the document id from epstein_list_documents or a search result. Returns page text with the page numbers needed to cite it.epstein_flight_log_search — Structured search over Epstein's pilot flight logbook (Government Exhibit 662-RR, USA v. Ghislaine Maxwell, 20-cr-330, S.D.N.Y.) — date, aircraft, tail number, route and the pilot's own passenger/remarks entry for each leg. Passenger initials and names are returned EXACTLY as the pilot wrote them ('JE, GM, SK') — never resolved to a full identity, per design decision C on this build. A token the transcriber could read but not confirm carries a trailing '[?]'; a wholly unreadable token is '[illegible]' — neither stands in for a guessed identity. Only 397 of an estimated 3,000+ logged legs are ingested (23 of 118 exhibit pages, spanning 1991-2005) because the rest requires further page-by-page visual transcription — call epstein_flight_log_search with no filters to see exactly which pages are covered before concluding an absence. Use it to find who is logged on a given tail number, route or date range, or to search the remarks text for a name or initials.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/epstein/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io