@pipeworx/epo-ops

European Patent Office Open Patent Services MCP — published patents from the EPO worldwide patent register (DocDB). Covers Europe and, via INPADOC family data, related filings across many jurisdictions worldwide — including PCT international applications (publications beginning "WO"): this is Pipeworx's PCT source (ruled 2026-10-18, no WIPO PCT webservice purchase). For US-only filings use the patents pack (USPTO ODP) instead — it doesn't overlap with this one on claims/citation coverage: this pack has get_claims, that one doesn't.

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

This pack does not carry a PCT application's International Search Report (ISR) or Written Opinion — the EPO's worldwide data service doesn't hold that document at all. For the ISR/Written Opinion itself, go to WIPO PATENTSCOPE instead.

Tools

• search_patents(query, range?) — CQL search against published patents (EP, US, CN, JP, KR, WO/PCT and 100+ other offices)
• get_biblio(number, format?) — bibliographic data
• get_family(number, raw?) — INPADOC family: a flat list of every related publication worldwide (country, kind, date, application number, priority claims), with a member count and the countries covered given first; raw:true also returns the underlying OPS payload
• get_abstract(number) — abstract text
• get_claims(number) — claims text
• get_legal_status(number) — INPADOC legal status: grant, lapse, opposition, withdrawal, appeal and renewal-fee events, grouped per family member/contracting state

Every number argument accepts a publication number in any printed form — "WO2025028566", "WO 2025/028566", "WO2025028566A1" all resolve to the same record. get_family additionally accepts a WIPO-style PCT application number before it has published, e.g. "PCT/US2024/012345" — this resolves to the receiving office's own application record and reports which form it matched.

Auth

• Platform key: gateway env PLATFORM_EPO_KEY (consumer_key:consumer_secret pair joined with colon)
• BYO: ?_apiKey=<consumer_key>:<consumer_secret> after registering at https://developers.epo.org/

The pack exchanges credentials for a bearer token (20-min TTL, cached).

Data source

Publisher: the European Patent Office (EPO). Dataset: Open Patent Services (OPS) — the EPO's worldwide bibliographic, full-text and legal-status data service, built on DOCDB (100+ patent offices, including WIPO/PCT) and INPADOC family and legal-event data. OAuth2 client-credentials auth; responses are rendered as JSON.

Patent number formats: EPO docdb (EP.1234567.A1), epodoc (EP1234567), original (EP1234567B1).

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/epo-ops/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 1856+ 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/epo_ops_search_patents \
  -H 'Content-Type: application/json' \
  -d '{"query":"ta=hydrogen fuel cell"}'

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

Run it from npm

@pipeworx/mcp-epo-ops is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/epo-ops/mcp endpoint shown above. It needs network access; there is no offline mode.

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

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 Epo Ops data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT