MongoDB MCP Server

Instructions

Implementation Reference

• src/index.ts:1591-1649 (handler)

  Handler for the 'text_search' tool that executes MongoDB $text search queries with optional filters, score inclusion, and limit. Includes error handling for missing text indexes.
  case 'text_search': { const { database, collection, searchText, filter, limit, includeScore } = request.params .arguments as { database?: string; collection: string; searchText: string; filter?: object; limit?: number; includeScore?: boolean; }; const dbName = database || this.defaultDatabase; if (!dbName) { throw new McpError( ErrorCode.InvalidRequest, 'Database name is required when no default database is configured' ); } const db = client.db(dbName); try { const searchQuery = { $text: { $search: searchText }, ...(filter || {}), }; const projection = includeScore ? { score: { $meta: 'textScore' } } : undefined; let query = db.collection(collection).find(searchQuery); if (projection) { query = query.project(projection); } if (includeScore) { query = query.sort({ score: { $meta: 'textScore' } }); } if (limit) { query = query.limit(limit); } const results = await query.toArray(); return { content: [ { type: 'text', text: JSON.stringify(results, null, 2), }, ], }; } catch (error) { // Check if error is due to missing text index if (error instanceof Error && error.message.includes('text index')) { throw new McpError( ErrorCode.InvalidRequest, 'No text index found on this collection. Create a text index first using db.collection.createIndex({ "field": "text" })' ); } throw error; } }
• src/index.ts:970-1001 (schema)

  Input schema for the text_search tool defining parameters: database (optional), collection (required), searchText (required), filter (optional), limit (1-1000), includeScore (boolean).
  inputSchema: { type: 'object', properties: { database: { type: 'string', description: 'Database name (optional if default database is configured)', }, collection: { type: 'string', description: 'Collection name', }, searchText: { type: 'string', description: 'Text to search for', }, filter: { type: 'object', description: 'Additional MongoDB query filter (optional)', }, limit: { type: 'number', description: 'Maximum number of results to return (optional)', minimum: 1, maximum: 1000, }, includeScore: { type: 'boolean', description: 'Include text search score in results (optional)', }, }, required: ['collection', 'searchText'], },
• src/index.ts:946-1002 (registration)

  Registration of the 'text_search' tool in the ListTools response, including name, detailed description, usage example, and input schema.
  name: 'text_search', description: `Perform a full-text search on a collection. Requirements: - Collection must have a text index - Only one text index per collection is allowed Features: - Supports phrases and keywords - Word stemming - Stop words removal - Text score ranking Example: use_mcp_tool with server_name: "mongodb", tool_name: "text_search", arguments: { "collection": "articles", "searchText": "mongodb database", "filter": { "published": true }, "limit": 10, "includeScore": true }`, inputSchema: { type: 'object', properties: { database: { type: 'string', description: 'Database name (optional if default database is configured)', }, collection: { type: 'string', description: 'Collection name', }, searchText: { type: 'string', description: 'Text to search for', }, filter: { type: 'object', description: 'Additional MongoDB query filter (optional)', }, limit: { type: 'number', description: 'Maximum number of results to return (optional)', minimum: 1, maximum: 1000, }, includeScore: { type: 'boolean', description: 'Include text search score in results (optional)', }, }, required: ['collection', 'searchText'], }, },