Patent Intelligence MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Patent Intelligence MCPsearch for patents on CRISPR technology"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
| $0.01 | Search by keyword, assignee, CPC, date, type |
| free | Full record: claims, citations, inventors |
| $0.01 | Portfolio: count, filing velocity, tech areas, recent filings |
| $0.01 | CPC classes ranked by filing volume, with top assignees |
| $0.02 | Semantic similarity over abstracts (pgvector) — premium |
| $0.02 | Structured daily patent-filing digest |
| 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.
Related MCP server: patent-mcp
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
This server cannot be installed
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/FoundryNet/patent-intel-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server