A FastMCP server for accessing United States Patent and Trademark Office (USPTO) patent and patent application data through multiple APIs including the Patent Public Search API, the Open Data Portal (ODP) API, PTAB API v3, PatentsView API, Office Action APIs, and Patent Litigation APIs. Using this server, Claude Desktop can pull data from USPTO APIs, search through PTAB proceedings and decisions, analyze patent litigation, research prosecution history, and more:

For an introduction to MCP servers see Introducing the Model Context Protocol.

Special thanks to Parker Hancock, author of the amazing Patent Client project, for blazing the trail to understanding of the string of requests and responses needed to pull data through the Public Search API.

This server provides 51 tools across 6 USPTO data sources for:

1. Patent Search - Full-text search of granted patents and published applications via PPUBS and PatentsView
2. Full Text Documents - Get complete text of patents including claims, description, and specification
3. PDF Downloads - Download patents as PDF files (Claude Desktop doesn't support this as a client currently)
4. Prosecution History - Access office actions, transactions, and file wrapper data
5. PTAB Proceedings - Search and retrieve Patent Trial and Appeal Board proceedings (IPR, PGR, CBM), decisions, and appeals
6. Office Actions - Access full-text office actions, citations, and rejection data
7. Patent Litigation - Search 74,000+ district court patent cases
8. Citation Analysis - Get enriched citation data and metrics
9. Patent Family Data - Continuity information, foreign priority, and related applications
10. Inventor/Assignee Search - Disambiguated inventor and assignee data via PatentsView

This server interacts with six USPTO patent data sources:

• Python 3.10-3.13 (3.12 recommended)
• Claude Desktop (for integration). Other models and MCP clients have not been tested.
• UV for Python version and dependency management

If you're a Python developer but still unfamiliar with uv, you're in for a treat. It's faster and easier than having a separate Python version manager (like pyenv) and setting up, activating, and maintaining virtual environments with venv and pip.

If you don't already have uv installed:

curl -LsSf https://astral.sh/uv/install.sh | sh

1. Clone this repository:

   git clone https://github.com/riemannzeta/patent_mcp_server
   cd patent_mcp_server

2. Install dependencies with uv:

   uv sync

3. Verify installation:

   uv run patent-mcp-server

   Should output:

   INFO     Starting USPTO Patent MCP server with stdio transport
   

To use the api.uspto.gov tools (ODP, PTAB, Office Actions, Litigation), you need an Open Data Portal API key:

1. Visit USPTO's Getting Started page and follow the instructions to request an API key.

2. Create a .env file in the patent_mcp_server directory:

   USPTO_API_KEY=your_actual_key_here

   Note: The PPUBS tools will work without this API key.

For advanced search with disambiguated inventor/assignee data:

1. Request an API key at PatentsView Support

2. Add to your .env file:

   PATENTSVIEW_API_KEY=your_patentsview_key

The server can be configured using environment variables in your .env file. All settings are optional with sensible defaults:

# API Keys
USPTO_API_KEY=your_key_here
PATENTSVIEW_API_KEY=your_patentsview_key  # Optional

# Logging
LOG_LEVEL=INFO  # Options: DEBUG, INFO, WARNING, ERROR, CRITICAL

# HTTP Settings
REQUEST_TIMEOUT=30.0  # Request timeout in seconds
MAX_RETRIES=3         # Maximum number of retry attempts
RETRY_MIN_WAIT=2      # Minimum wait time between retries (seconds)
RETRY_MAX_WAIT=10     # Maximum wait time between retries (seconds)

# Session Management
SESSION_EXPIRY_MINUTES=30  # How long to cache ppubs sessions
ENABLE_CACHING=true        # Enable/disable session caching

# API Endpoints (usually don't need to change)
PPUBS_BASE_URL=https://ppubs.uspto.gov
API_BASE_URL=https://api.uspto.gov
PATENTSVIEW_BASE_URL=https://search.patentsview.org
OFFICE_ACTION_BASE_URL=https://developer.uspto.gov

To integrate this MCP server with Claude Desktop:

1. Update your Claude Desktop configuration file (claude_desktop_config.json):

   {
     "mcpServers": {
       "patents": {
         "command": "uv",
         "args": [
           "--directory",
           "/Users/username/patent_mcp_server",
           "run",
           "patent-mcp-server"
         ]
       }
     }
   }

   You can find claude_desktop_config.json on a Mac by opening the Claude Desktop app, opening Settings (from the Claude menu or by Command + ' on the keyboard), clicking "Developer" in the sidebar, and "Edit Config."

2. Replace /Users/username/patent_mcp_server with the actual path to your patent_mcp_server directory.

When integrated with Claude Desktop, the server will be automatically started when needed and doesn't need to be run separately.

To integrate this mCP server with Claude Code for a particular project, from the project root:

claude mcp add-json patents '{"command": "uv", "args": ["--directory", "/Users/michael.frank.martin/patent_mcp_server", "run", "patent-mcp-server"]}'

If you're already running Claude Code, you'll have to /exit and restart. Then /mcp to verify that it's configured.

The server also provides MCP Resources (accessible via @ mentions):

• patents://cpc/{code} - CPC classification information
• patents://status-codes - USPTO status code definitions
• patents://sources - Data source information
• patents://search-syntax - Query syntax guide

And MCP Prompts (workflow templates):

• prior_art_search - Comprehensive prior art search guide
• patent_validity - Patent validity analysis workflow
• competitor_portfolio - Competitor portfolio analysis
• ptab_research - PTAB proceeding research guide
• freedom_to_operate - FTO analysis workflow
• patent_landscape - Technology landscape mapping

The project includes comprehensive test suites:

# Run unit tests (default - skips integration tests)
uv run pytest

# Run with verbose output
uv run pytest -v

# Run integration tests (requires network access)
uv run pytest -m integration

# Run all tests including integration
uv run pytest -m ""

# Run with coverage report
uv run pytest --cov=patent_mcp_server

Test results are stored in /test/test_results/.

To install development dependencies:

uv sync --dev

• Added PatentsView attorney search tools (patentsview_search_attorneys, patentsview_get_attorney)
• Added PatentsView IPC classification tools (patentsview_lookup_ipc, patentsview_search_by_ipc)
• Fixed bug in search_publications method (pagination options not being passed)
• Added new PatentsView API endpoints (attorney, IPC, pregrant publication text, citations)
• Updated README with complete tool documentation

• PyPI release preparation

• Focused on USPTO-only data sources
• Renamed ODP tools with odp_ prefix for clarity
• Improved function signatures (using query instead of q)
• Enhanced test organization with proper integration test markers
• Updated validation with Pydantic models

• Added 33 new tools (PTAB, PatentsView, Office Actions, Citations, Litigation)
• Rate limiting support for PatentsView API
• Comprehensive async client architecture

• Centralized configuration with environment variables
• Standardized error handling
• Input validation with Pydantic
• Retry logic with exponential backoff
• Session caching for PPUBS

MIT