arxiv-search-MCP-Server

# arxiv-search MCP Server <a href="https://youtu.be/vYm0brFoMwA">🚀</a> ### 🚀stoeng English | 中文 <a name="english"></a> A Model Context Protocol server for searching academic papers on arXiv. This server provides tools to search for academic papers on arXiv and access detailed information about them. It demonstrates core MCP concepts by providing: - Resources representing academic papers with URIs and metadata - Tools for searching papers with customizable parameters - Support for sorting and pagination of search results ## Features ### Resources - List and access papers via `arxiv://paper/{id}` URIs - Each paper has title, authors, summary, publication date, and PDF link - JSON mime type for structured content access ### Tools - `search_papers` - Search for academic papers on arXiv - Takes query as required parameter - Optional parameters for max results, sorting, and pagination - Returns formatted results with paper details ## Development Install dependencies: ```bash npm install ``` Build the server: ```bash npm run build ``` For development with auto-rebuild: ```bash npm run watch ``` ## Installation To use with Claude Desktop, add the server config: On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json` On Windows: `%APPDATA%/Claude/claude_desktop_config.json` ```json { "mcpServers": { "arxiv-search": { "command": "node", "args": ["/path/to/arxiv-search/build/index.js"], "disabled": false, "alwaysAllow": [] } } } ``` To use with VSCode and Roo Cline, add to: `~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json` ### Debugging Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script: ```bash npm run inspector ``` The Inspector will provide a URL to access debugging tools in your browser. ## Usage Examples ``` <use_mcp_tool> <server_name>arxiv-search</server_name> <tool_name>search_papers</tool_name> <arguments> { "query": "machine learning", "max_results": 5, "sort_by": "relevance" } </arguments> </use_mcp_tool> ``` Available parameters: - `query` (required): Search query (e.g., 'machine learning', 'quantum physics') - `max_results` (optional): Maximum number of results to return (default: 10, max: 100) - `sort_by` (optional): Sort method ('relevance', 'lastUpdatedDate', 'submittedDate') - `start` (optional): Starting index for results (for pagination) --- <a name="中文"></a>