
Patents Mcp
Taps into the Google Patents public dataset on BigQuery to give Claude patent search and prior art discovery. You get three tools: keyword and inventor search across patents, full patent retrieval by publication number, and claims text extraction. Built in Go, uses a service account with BigQuery Job User and Data Viewer roles, and leans on the 1TB monthly free tier. Good for researching existing patents before filing, finding prior art for patent applications, or exploring what companies have filed in specific tech areas. The architecture keeps each tool self-contained, so extending it with new queries is straightforward.
- GitHub stars
- 2
- tools
- 3
- last updated
- May 21, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
search_patentsSearch patents by keyword, technology area, or inventor name
Search patents by keyword, technology area, or inventor name
No parameter schema in public metadata yet.
get_patentFetch full patent details by publication number
Fetch full patent details by publication number
No parameter schema in public metadata yet.
get_patent_claimsFetch patent claims text
Fetch patent claims text
No parameter schema in public metadata yet.
Sponsors
Readme
patents-mcp
An MCP (Model Context Protocol) server for patent search and prior art discovery, powered by the Google Patents public dataset on BigQuery.
Built with the official Go MCP SDK.
Why patents-mcp?
Existing patent MCP servers are either paid, single-source, or unmaintained. patents-mcp is:
- Free — built on Google Patents public dataset (1TB/month free on BigQuery)
- Open source — MIT licensed
- Production grade — structured logging, graceful shutdown, clean architecture
- Extensible — each tool is self-contained, easy to add new tools
Available Tools
Details
- Repository
- github.com/tushariitr-19/patents-mcp
- Categories
- Search & Web Crawling, Data & Analytics
- Registry
- MCP registry, active