Mongodb MCP Server

🚀 MongoDB MCP Server

A Model Context Protocol (MCP) server that provides read-only access to MongoDB databases. This server enables LLMs to examine collection schemas and execute aggregation pipelines.

🚀 Quick Start

This is a community-maintained MCP server. 👉 To access the official MongoDB MCP server, visit mongodb-js/mongodb-mcp-server.

✨ Features

• A Model Context Protocol (MCP) server offering read - only access to MongoDB databases.
• Allows LLMs to check collection schemas and execute aggregation pipelines.

📦 Installation

To use this server with the Claude Desktop application, add the following configuration to the "mcpServers" section of the claude_desktop_config.json file:

"mongodb": {
      "command": "npx",
      "args": [
        "-y" ,
        "@pash1986/mcp-server-mongodb"
      ],
     "env" : {
	"MONGODB_URI" : "mongodb+srv://<yourcluster>" // 'mongodb://localhost:27017'
	}
    }

Replace mydb with your database name and adjust the connection string as needed.

💻 Usage Examples

Basic Usage

Basic Aggregation

{
  "collection": "users",
  "pipeline": [
    { "$match": { "age": { "$gt": 21 } } },
    { "$group": {
      "_id": "$city",
      "avgAge": { "$avg": "$age" },
      "count": { "$sum": 1 }
    }},
    { "$sort": { "count": -1 } },
    { "$limit": 10 }
  ],
  "options": {
    "allowDiskUse": true,
    "maxTimeMS": 60000,
    "comment": "City-wise user statistics"
  }
}

Query Explanation

{
  "collection": "users",
  "pipeline": [
    { "$match": { "age": { "$gt": 21 } } },
    { "$sort": { "age": 1 } }
  ],
  "verbosity": "executionStats"
}

🔧 Technical Details

Tools

• aggregate

  • Execute a MongoDB aggregation pipeline on the connected database.
  • Input:
    • collection (string): The collection to query.
    • pipeline (array): MongoDB aggregation pipeline stages.
    • options (object): Optional aggregation settings.
      • allowDiskUse (boolean): Allow disk operations.
      • maxTimeMS (number): Maximum execution time in milliseconds.
      • comment (string): A comment to identify the operation.
  • The default document limit is 1000 if no limit stage is specified.
  • The default timeout is 30 seconds.

• explain

  • Get the execution plan of an aggregation pipeline.
  • Input:
    • collection (string): The collection to analyze.
    • pipeline (array): MongoDB aggregation pipeline stages.
    • verbosity (string): The level of detail for the explanation.
      • Options: "queryPlanner", "executionStats", "allPlansExecution".
      • Default: "queryPlanner".

Resources

The server provides schema information for each database collection:

• Collection Schema (mongodb://<host>/<collection>/schema)
  • Derived JSON schema information for the collection.
  • Includes field names and data types.
  • The schema is derived from sample documents.

🔒 Security Features

• If no limit is specified in the pipeline, the default limit is 1000 documents.
• The default timeout for all operations is 30 seconds.
• All operations are read - only.
• Schema inference is done from a safe sample of the collection.

📄 License

This MCP server is released under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, see the LICENSE file in the project repository.