uspto_enriched_citation_mcp
High-performance MCP server for USPTO Enriched Citation API v3 with AI-powered data extraction, token-saving context reduction, progressive disclosure workflows, and seamless cross-MCP integration
claude mcp add --transport stdio john-walkoe-uspto_enriched_citation_mcp uv --directory C:/path/to/uspto_enriched_citation_mcp run uspto_enriched_citation_mcp \ --env USPTO_API_KEY="your_actual_api_key_here"
How to use
This MCP server provides fast access to USPTO Enriched Citation API v3 data with token-saving context reduction and progressive disclosure workflows. It exposes discovery-oriented search functions that help you quickly identify relevant citations and then drill down into detailed analysis as needed. The available functions include search_citations_minimal for ultra-fast discovery with essential fields and search_citations_balanced for deeper, more comprehensive analysis. The server is designed to integrate across multiple MCPs, enabling cross-referencing with prosecution histories, PTAB data, and knowledge bases. To use it, ensure you have an USPTO_API_KEY and point your client at the running MCP endpoint; authenticate via the included API key mechanism, and then invoke the discovery and analysis workflows described in the available documentation prompts and usage guides.
How to install
Prerequisites:
- Python 3.11+ installed on your system
- uv (the MCP runtime) installed and available in your PATH
- Access to an USPTO API key
-
Clone the repository: git clone https://github.com/john-walkoe/uspto_enriched_citation_mcp.git cd uspto_enriched_citation_mcp
-
Install dependencies (via your preferred method, e.g., pipx or pip): python -m pip install --upgrade pip python -m pip install uv || pip install uv
-
Prepare your environment variables:
- Create a secure method to store USPTO_API_KEY (recommended): export USPTO_API_KEY=your_actual_api_key_here
- Alternatively, populate the key in a deployment-specific environment file as allowed by your runtime
-
Run the MCP server locally (example with uv): uv --directory /path/to/uspto_enriched_citation_mcp run uspto_enriched_citation_mcp
-
Verify the server is running by sending a test request to the MCP endpoint or by following the INSTALL.md guidance for validation tests.
-
For Claude Desktop integration or cross-MCP usage, ensure the server name aligns with your deployment and that the environment variable is accessible to the hosting process.
Additional notes
Tips and considerations:
- Ensure your USPTO_API_KEY is kept secure and not committed to source control. Use secure storage or environment-based configuration.
- The server supports token-saving context reduction to optimize search results; you may adjust field sets and prompts to balance speed and depth according to your needs.
- If using cross-MCP workflows, configure links to related MCPs (Patent File Wrapper, PTAB, etc.) to enable seamless navigation across systems.
- Common issues include API key misconfiguration, network access restrictions, and permission problems when starting the uv runtime. Refer to INSTALL.md and SECURITY_GUIDELINES.md for troubleshooting and best practices.
- When upgrading, review any changes in the available search functions and field mappings to ensure compatibility with existing client queries.
Related MCP Servers
mcp-nixos
MCP-NixOS - Model Context Protocol Server for NixOS resources
pasal
The first open, AI-native Indonesian legal platform. MCP server + web app giving Claude grounded access Indonesian laws.
python-notebook
Lightweight Python Notebook MCP - Enable AI assistants to create, edit, and view Jupyter notebooks via Model Context Protocol
daisyui
🌼 A token-friendly local MCP server for DaisyUI component documentation using their public llms.txt.
youtube
A comprehensive Model Context Protocol (MCP) server providing real-time YouTube Data API access for AI assistants. Features 14 functions including intelligent content evaluation with technology freshness scoring for knowledge base curation.
computeruseprotocol
Computer Use Protocol is a universal schema for AI agents to perceive and interact with any desktop UI.