MongoDB MCP server

The MongoDB MCP Server provides read-only access to MongoDB databases, allowing Large Language Models (LLMs) to inspect collection schemas and execute aggregation pipelines. This server implements the Model Context Protocol, making it possible for AI assistants to interact with your MongoDB data.

Installation

To use the MongoDB MCP Server, you'll need to add it to your Claude Desktop configuration. Follow these steps:

1. Ensure you have Node.js installed on your system
2. Add the server configuration to your Claude Desktop settings

Claude Desktop Configuration

Add the following configuration to the "mcpServers" section of your claude_desktop_config.json file:

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

Replace <yourcluster> with your MongoDB connection string. For a local MongoDB instance, you might use mongodb://localhost:27017.

Using the MCP Server

The MongoDB MCP Server provides two main tools and collection schema resources.

Available Tools

Aggregate Tool

The aggregate tool allows you to execute MongoDB aggregation pipelines against your database.

Input parameters:

• collection (string): The collection to query
• pipeline (array): MongoDB aggregation pipeline stages
• options (object): Optional aggregation settings
  • allowDiskUse (boolean): Allow operations that require disk usage
  • maxTimeMS (number): Maximum execution time in milliseconds
  • comment (string): Comment to identify the operation

Example:

{
  "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"
  }
}

Explain Tool

The explain tool helps you understand how MongoDB will execute your queries by providing execution plans.

Input parameters:

• collection (string): The collection to analyze
• pipeline (array): MongoDB aggregation pipeline stages
• verbosity (string): Detail level of the explanation
  • Options: "queryPlanner", "executionStats", "allPlansExecution"
  • Default: "queryPlanner"

Example:

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

Accessing Collection Schemas

The server automatically provides schema information for each collection in your database. These schemas are inferred by sampling the collection's documents and include field names and data types.

Collection schemas are available at: mongodb://<host>/<collection>/schema

Safety Features

The MongoDB MCP Server incorporates several safety features:

• Operations are read-only to protect your data
• Automatic limit of 1000 documents if no limit is specified in the pipeline
• Default timeout of 30 seconds for all operations
• Safe schema inference from collection samples

These measures ensure that the server can be used safely with LLMs without risking data integrity or performance issues.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

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

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect