Search 200M+ patents and scientific literature in natural language directly inside Claude, Cursor, or any MCP-compatible AI tool. Powered by PatSnap's global R&D intelligence database.

Prototype: An end-to-end learning project demonstrating a multi-agent MCP RAG pipeline that analyzes existing patents and suggests how to refine ideas to make them novel and potentially patentable.

Detect potential patentable technical inventions in Git diffs, rank prior art, and produce attorney-reviewable claim drafts in CI.

PatentLLM generates R&D-focused patent intelligence reports from patent PDFs using section-aware parsing, embedding retrieval, local LLMs, claim-bank grounding, and citation-alignment audits.

Patent intelligence for AI agents — patent search, USPTO data, patent landscape & pgvector prior-art search. MCP + x402.