@pipeworx/trademarks

US federal trademarks: find marks by text or owner, look one up by serial or registration number, and read its status, owners of record, attorney of record, classes and goods/services. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1857+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• search_trademarks(query?, owner?, international_class?, live_only?, limit?, offset?) -- knockout / clearance search by mark text, or an owner's portfolio when only owner is given (e.g. {"owner":"Nike","live_only":true}). A zero-hit search says what it did NOT search instead of reading as "this name is free".

• get_trademark_by_serial(serial_number, api_key?) -- one mark by its 8-digit serial number (e.g. 79153306).

• get_trademark_by_registration(registration_number, api_key?) -- one mark by its registration number (e.g. 4872338).

• get_trademark_documents(serial_number, api_key) -- the prosecution document list (office actions, responses). Needs a TSDR key.

Number lookups answer {found:true, source, data_as_of, record} or {found:false, reason, hint} (not_in_register, invalid_number, upstream_unavailable) -- never an empty object.

Related MCP server: INPI MCP Server

Auth

Keyless for search and both number lookups. A caller who holds a free USPTO TSDR key (account.uspto.gov/api-manager) can pass api_key to get TSDR's own case-status record from the number lookups instead; get_trademark_documents requires one.

Data sources

• USPTO, US federal trademark register (Trademark Search). The register index behind USPTO's Trademark Search system (the TESS replacement): about 13.3 million application and registration records, 4.6 million of them live (measured 2026-10-28), refreshed by USPTO daily -- the newest record load seen on 2026-10-28 was 2026-10-27, carrying filings from 2026-10-26. data_as_of is USPTO's own per-record load timestamp.

• USPTO, Trademark Status and Document Retrieval (TSDR) -- only when a caller supplies a key.

US federal data, public domain.

Personal data

US trademark owners include natural persons, and the register carries every owner's full postal address. This pack serves owner names, role, legal entity type, citizenship and the attorney of record, as the register shows them. It never serves a street address for anyone. City / state / country is served for organisations only; an individual, sole proprietor, joint owner or an owner whose entity type is blank gets location: null. The filter lives in src/owners.ts and is pinned by src/index.test.ts.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/trademarks/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 1857+ 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/search_trademarks \
  -H 'Content-Type: application/json' \
  -d '{"query":"TenderBrief","live_only":true,"international_class":"35"}'

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

Run it from npm

@pipeworx/mcp-trademarks 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/trademarks/mcp endpoint shown above. It needs network access; there is no offline mode.

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

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 Trademarks data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT