A professional tool enabling deep, integrated search across the Patsnap global patent and literature databases simultaneously. It supports natural language queries, semantic search, and keyword search, backed by precise pre-filtering capabilities for efficient and accurate retrieval of scientific and patent intelligence. This MCP also allows users to fetch basic bibliographic data for patents or literature in Markdown format.
Professional patent and academic paper search tool supporting semantic queries, keyword search, and multi-dimensional filtering. Core capabilities include natural language query, precise keyword matching, BM25-based text search, and filtering by assignee, IPC classification, date, jurisdiction, etc.
semantic_querystringThe technical problem or concept to be searched, described in natural language.
search_strategyarraySearch strategy combination. Available values: 'semantic', 'keyword', 'filter'.
keywordsarrayList of technical terms used for BM25 keyword matching.
offsetintegerPagination offset, number of leading results to skip. Must be >= 0. Constraint: offset + limit <= 1000.
limitintegerPage size, number of results to return in this page. Range: 1-100. Constraint: offset + limit <= 1000.
sourcestringSingle data source to search. 'patent' means patents; 'paper' means papers. To cover both patents and papers, make two separate calls.
filtersobjectStructured filter conditions used to narrow down the search results.
sortstringResult ordering. Default is relevance. Patent supports publication, application, granted, expired, priority, cited_count; paper supports publication and cited_count. Prefix '-' means descending.
A professional data retrieval tool for patents and literatures. It fetches Markdown-formatted content via URLs or publication numbers (patents only). For patent data, it retrieves bibliographic details, claims, descriptions, and accompanying drawings. For literatures, it provides basic abstract metadata.
/fetchA professional tool enabling deep, integrated search across the Patsnap global patent and literature databases simultaneously. It supports natural language queries, semantic search, and keyword search, backed by precise pre-filtering capabilities for efficient and accurate retrieval of scientific and patent intelligence. This MCP also allows users to fetch basic bibliographic data for patents or literature in Markdown format.
Get a Patsnap Open Platform API key, copy the MCP connection URL from the Connect panel on this page, and add the server to Cursor, Claude Desktop, or another Model Context Protocol-compatible AI agent client.
{
"mcpServers": {
"patsnap_patent_literature_search": {
"url": "https://connect.patsnap.com/2b0355/logic-mcp?apikey={your_api_key}"
}
}
}