Patent Intelligence MCP
Enables AI agents to perform patent search, portfolio analysis, technology trend tracking, and semantic prior-art search using USPTO data.
README
Patent Intelligence MCP
Patent intelligence for AI agents — patent search, USPTO data, patent landscape, technology trends, and semantic prior-art search (pgvector) over USPTO PatentsView data.
Part of the FoundryNet Data Network. Attest your agent's research with MINT Protocol for verifiable, on-chain proof of work. See also: gov-contracts-mcp, brand-intel-mcp.
Live MCP endpoint (Streamable HTTP):
https://patent-intel-mcp-production.up.railway.app/mcp
Tools
| Tool | Price | What it does |
|---|---|---|
search_patents |
$0.01 | Search by keyword, assignee, CPC, date, type |
patent_detail |
free | Full record: claims, citations, inventors |
company_patents |
$0.01 | Portfolio: count, filing velocity, tech areas, recent filings |
trending_technology |
$0.01 | CPC classes ranked by filing volume, with top assignees |
prior_art_search |
$0.02 | Semantic similarity over abstracts (pgvector) — premium |
daily_digest |
$0.02 | Structured daily patent-filing digest |
mint_info |
free | FoundryNet Data Network + MINT Protocol details |
Free tier: 25 paid-tool queries/day per agent (plus free patent_detail +
mint_info). Pass agent_id to scope your allowance. After that, x402: the tool
returns an HTTP-402 with a payment memo — send the USDC on Solana with that memo,
then re-call with the same args plus payment_tx=<signature>. An
Authorization: Bearer fnet_… key bypasses the paywall.
How it works
A daily task (~5am PT) ingests patents granted in the last day from the USPTO
PatentsView Search API, maps them to a normalized schema, embeds abstracts with
fastembed (BAAI/bge-small-en-v1.5, local, no API key), and stores them in a
standalone Supabase project. prior_art_search embeds your query and ranks by
pgvector cosine similarity. A rolling patent_assignees summary powers
company_patents.
Honesty note: claims_count isn't exposed by the PatentsView patent endpoint,
so it's left null (a future enrichment hook); citation_count and the rest come
straight from PatentsView.
Connect
Smithery: @foundrynet/patent-intel · MCP registry: io.github.FoundryNet/patent-intel-mcp
{ "mcpServers": { "patent-intel": { "url": "https://patent-intel-mcp-production.up.railway.app/mcp" } } }
Built by FoundryNet · hello@foundrynet.io
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.