The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Patents listing page.
The US Patent and Trademark Office's patent database via the PatentsView API. Search and retrieve granted US patents (and published applications) by keyword, assignee, inventor, or patent number. ~12 million issued patents going back to 1976. Free, no auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Patents are the public record of what's been invented and who claims to have invented it. For competitive intelligence, IP due diligence, freedom-to-operate research, or technology landscaping, the USPTO is the source. The data is structured: claims, citations, family members, prosecution history, assignment changes.
Two core flows:
1. Keyword search. "What patents exist for CRISPR gene editing?" → search_patents({query: "CRISPR gene editing"}) → top patents by relevance with title, abstract, assignee, filing date, patent number.
2. Specific patent. "What's in patent US 10,123,456?" → get_patent({number: "US10123456"}) → full record: claims, citations, family, current owner.
For company-level IP due diligence (combining patents with SEC IP risk disclosures and trademarks), see the Patent Due Diligence recipe.
Patent numbers are stable forever. Embed in agent output as the canonical citation.
| Type | Prefix | What it is |
|---|---|---|
| Utility patent | (none / numeric) | Standard invention patent (machines, processes, articles) |
| Design patent | D | Ornamental design (e.g., D123,456 = a chair design) |
| Plant patent | PP | Asexually reproduced plant variety |
| Reissue | RE | Corrected version of an earlier patent |
| Reexamination | (E numbers) | Validity-challenged patents under review |
The default search returns utility patents. For design or plant patents, filter by type in results.
Cache-Control: no-cache.search_patents finds patents whose text mentions your terms. It does not tell you whether a patent CLAIMS what you'd be doing. FTO requires reading claims carefully — Pipeworx returns them, but interpretation needs a patent attorney.pipeworx_feedback if you need them.grant_date, not filing_date. Applications can be rejected or amended; the issued patent is what matters.Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
tools/list at https://gateway.pipeworx.io/patents/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:
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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:
The gateway picks the right tool and fills the arguments automatically.
MIT