Patent search and prior art discovery via Google Patents on BigQuery
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"patents-mcp": {
"env": {
"GCP_PROJECT_ID": "your-gcp-project-id",
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json"
},
"command": "/path/to/patents-mcp-server"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
An MCP (Model Context Protocol) server for patent search and prior art discovery, powered by the Google Patents public dataset on BigQuery.
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in data / legal
Manage Supabase projects — databases, auth, storage, and edge functions
Query and manage PostgreSQL databases directly from AI assistants
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases
MCP Security Weekly
Get CVE alerts and security updates for io.github.tushariitr-19/patents-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
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.
Existing patent MCP servers are either paid, single-source, or unmaintained. patents-mcp is:
| Tool | Description |
|---|---|
search_patents | Search patents by keyword, technology area, or inventor name |
get_patent | Fetch full patent details by publication number |
get_patent_claims | Fetch patent claims text |
BigQuery Job UserBigQuery Data Viewergit clone https://github.com/tushariitr-19/patents-mcp
cd patents-mcp
go build -o patents-mcp-server ./cmd/server/
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
export GCP_PROJECT_ID="your-gcp-project-id"
# Optional: enable debug logging
export DEBUG=true
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"patents-mcp": {
"command": "/path/to/patents-mcp-server",
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json",
"GCP_PROJECT_ID": "your-gcp-project-id"
}
}
}
}

Once connected to Claude Desktop:
patents-mcp/
├── cmd/server/main.go ← entry point, env vars, graceful shutdown
├── server/server.go ← MCP server setup, tool registration
├── tools/
│ └── search.go ← search_patents tool (self-contained)
├── bigquery/
│ └── client.go ← BigQuery query execution
├── logger/
│ └── logger.go ← structured logging via zap
└── models/
└── patent.go ← shared Patent struct
Each tool owns its own dependencies — the server is agnostic of what tools do internally. Adding a new tool is a single line in server/server.go.
PRs welcome. To add a new tool:
tools/<toolname>.goserver/server.go with one lineMIT