Skip to content
Conduit

mcp server

mcp-hathitrust

HathiTrust Bibliographic API MCP.

pipeworx-io/mcp-hathitrustcommunitylistedunreviewed

Set up

Hosted by its author. Add the URL to your agent — nothing to install.

~/Library/Application Support/Claude/claude_desktop_config.json
Settings → Connectors → Add custom connector

Name: mcp-hathitrust
URL:  https://gateway.pipeworx.io/hathitrust/mcp

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 17, 2026

@pipeworx/hathitrust

HathiTrust's digitized-book holdings by standard identifier (OCLC, LCCN, ISSN, ISBN, HathiTrust item id, catalog record number): the bibliographic record plus every scanned copy, each flagged full-view (readable online) or limited (search-only).

Part of Pipeworx — an MCP gateway connecting AI agents to 1784+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

  • lookup_by_identifier(id_type, id): records and scanned copies for one identifier.
  • get_record(record_number): one catalog record with full bibliographic metadata.
  • check_full_view(id_type, id): whether a readable copy exists, with reading URLs.

Auth

Keyless upstream, but accounts only on Pipeworx. The manifest row carries accountOnly: true, so the gateway refuses anonymous callers and callers that send only an X-API-Key (BYO with no account) with account_required and a link to https://pipeworx.io/signup?via=hathitrust. OAuth and paid Bearer-token accounts, x402 payers and internal traffic (X-Pipeworx-Internal, so the monitor) keep full access. The refusal happens before the pack runs, so no request reaches HathiTrust for a refused caller.

Why (Bruce ruled 2026-10-13, fleet #2964): a residential proxy pool of ~171k IPs was enumerating HathiTrust's catalogue by OCLC number through REST /v1/tools/lookup_by_identifier, about 600k calls an hour, every IP kept under its per-IP limit. The pack had seen about 2 genuine calls a day. Per-IP limits cannot stop that shape, and an X-API-Key is never validated, so it is no identity either. The risk was HathiTrust blocking our egress for every caller. An account is the cheapest identity that cannot be minted in bulk.

Lifting it is a one-line manifest change (drop accountOnly), then node scripts/sync-pack-manifest.mjs. Ask Bruce first. The gate itself lives in workers/gateway/src/account-only.ts.

Data sources

  • HathiTrust Digital Library, Bibliographic API: catalog records and per-copy rights codes.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "hathitrust": {
      "url": "https://gateway.pipeworx.io/hathitrust/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/hathitrust/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1784+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/lookup_by_identifier \
  -H 'Content-Type: application/json' \
  -d '{"id_type":"isbn","id":"9780030110405"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/lookup_by_identifier. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "hathitrust": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-hathitrust"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-hathitrust

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Hathitrust data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

↑↓ navigate openesc close