Skip to main content
Glama

MCP Server Boilerplate

by ricleedo

mongo-create-document

Create new documents in MongoDB collections by specifying database, collection, and JSON document data for structured data insertion.

Instructions

Create a new document in a MongoDB collection

Input Schema

NameRequiredDescriptionDefault
collectionYesCollection name
databaseYesDatabase name
documentYesDocument to insert as JSON object

Input Schema (JSON Schema)

{ "properties": { "collection": { "description": "Collection name", "type": "string" }, "database": { "description": "Database name", "type": "string" }, "document": { "additionalProperties": {}, "description": "Document to insert as JSON object", "type": "object" } }, "required": [ "database", "collection", "document" ], "type": "object" }

Implementation Reference

  • The handler function for the 'mongo-create-document' tool. It ensures a connection to the specified database, retrieves the collection, inserts the provided document using MongoDB's insertOne method, and returns a success message with the inserted document's ID. Errors are caught and rethrown with context.
    async ({ database: dbName, collection: collectionName, document }) => { try { const db = await ensureConnection(dbName); const collection: Collection = db.collection(collectionName); const result = await collection.insertOne(document); return { content: [ { type: "text", text: `Document created successfully with ID: ${result.insertedId}`, }, ], }; } catch (error) { throw new Error(`Failed to create document: ${error instanceof Error ? error.message : 'Unknown error'}`); } }
  • Zod schema defining the input parameters for the tool: database name (string), collection name (string), and document (record/object to insert).
    { database: z.string().describe("Database name"), collection: z.string().describe("Collection name"), document: z.record(z.any()).describe("Document to insert as JSON object"), },
  • src/index.ts:102-129 (registration)
    Registration of the 'mongo-create-document' tool on the MCP server, specifying name, description, input schema, and handler function.
    server.tool( "mongo-create-document", "Create a new document in a MongoDB collection", { database: z.string().describe("Database name"), collection: z.string().describe("Collection name"), document: z.record(z.any()).describe("Document to insert as JSON object"), }, async ({ database: dbName, collection: collectionName, document }) => { try { const db = await ensureConnection(dbName); const collection: Collection = db.collection(collectionName); const result = await collection.insertOne(document); return { content: [ { type: "text", text: `Document created successfully with ID: ${result.insertedId}`, }, ], }; } catch (error) { throw new Error(`Failed to create document: ${error instanceof Error ? error.message : 'Unknown error'}`); } } );
  • Helper function to establish and cache MongoDB client connection and database instances, used by the tool handler.
    async function ensureConnection(dbName: string): Promise<Db> { if (!mongoClient) { const uri = getMongoUri(); mongoClient = new MongoClient(uri); await mongoClient.connect(); } if (!databases.has(dbName)) { databases.set(dbName, mongoClient.db(dbName)); } return databases.get(dbName)!; }

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/ricleedo/mongo-boilerplate-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server