uspto_pfw_mcp
Verified Safeby john-walkoe
Overview
This MCP server provides enhanced search capabilities and local PDF download functionality for USPTO Patent File Wrapper data, offering LLM guidance, secure proxy downloads, and integration points with other USPTO MCPs (FPD, PTAB, Citations).
Installation
python -m patent_filewrapper_mcpEnvironment Variables
- USPTO_API_KEY
- MISTRAL_API_KEY
- PFW_PROXY_PORT
- PROXY_PORT
- INTERNAL_AUTH_SECRET
- USPTO_TIMEOUT
- USPTO_DOWNLOAD_TIMEOUT
- MISTRAL_OCR_TIMEOUT
- USPTO_MAX_RETRIES_PER_HOUR
- ENABLE_ALWAYS_ON_PROXY
- ENABLE_PROXY_SERVER
- ENVIRONMENT
Security Notes
The server implements robust security measures. API keys are managed via Windows DPAPI (or secure file-based storage with 0o600 permissions on non-Windows) and environment variables, never exposed in client-facing URLs. The proxy server enforces IP whitelisting (localhost only), CORS restrictions, request size limits, and adds standard security headers. Internal communication relies on HMAC tokens with a shared secret. Sensitive data is protected through encryption (Fernet for proxy links). Placeholder API key detection helps prevent misconfiguration. A dedicated security logger with JSON formatting, rotation, and alerting is in place. While a legacy DPAPI module (secure_storage.py) still exists, it is clearly marked as deprecated and points to a more secure unified storage solution.
Similar Servers
Scrapling
Enables AI chatbots and agents to perform adaptive web scraping, extract targeted data, and bypass anti-bot protections conversationally.
kreuzberg
High-performance document intelligence for extracting text, metadata, and structured information from a wide range of document formats including PDFs, Office documents, images, and HTML. It supports advanced features like OCR, table extraction, chunking, language detection, and embedding generation, powered by a Rust core for native performance.
kreuzberg
High-performance document intelligence platform for extracting text, metadata, and structured information (tables, images, chunks) from over 50 diverse document formats (PDFs, Office, images, HTML, etc.). It offers advanced OCR capabilities, multilingual support, and features like chunking, embeddings, and keyword extraction. Functionality is exposed via multiple language bindings and a Micro-service Communication Protocol (MCP) server for flexible integration.
DevDocs
Provides intelligent web crawling and documentation extraction, storing content in a Model Context Protocol server for LLM querying and accelerating developer research.