MongoDB Model Context Protocol

Provides a MongoDB MCP server that enables querying, schema inspection, and data management via natural language.

typescript

1

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nickiiitu-mongodb-model-context-protocol-mcp-": {
      "command": "npx",
      "args": [
        "mongo-mcp",
        "mongodb://<username>:<password>@<host>:<port>/<database>?authSource=admin"
      ]
    }
  }
}

You can connect your MCP client to a MongoDB database and interact with collections, schemas, and documents through natural language. This MCP server lets you inspect collection schemas, query documents, manage indexes, and perform insert, update, and delete operations from your client prompts.

How to use

You connect using an MCP client such as Claude Desktop. Add an MCP server entry that points to either the local development runtime or the npm-based runtime, then start querying your MongoDB data through natural language prompts.

How to install

Prerequisites you need to have before running the MCP server:

Node.js 18+
npx
Docker and Docker Compose (for local sandbox testing only)
MCP Client (Claude Desktop App or another compatible client)

Local runtime configurations

{
  "mcpServers": {
    "mongodb": {
      "command": "node",
      "args": [
        "dist/index.js",
        "mongodb://root:example@localhost:27017/test?authSource=admin"
      ]
    }
  }
}

Remote (npm/npx) runtime configurations

{
  "mcpServers": {
    "mongodb": {
      "command": "npx",
      "args": [
        "mongo-mcp",
        "mongodb://<username>:<password>@<host>:<port>/<database>?authSource=admin"
      ]
    }
  }
}

Test sandbox setup

If you want to run a local sandbox MongoDB instance, you can start it with Docker Compose and seed it with sample data.

Start the MongoDB sandbox:

docker-compose up -d

Seed the database with test data:

npm run seed

Available tools

find

Query documents with filtering and projection

listCollections

List available collections

insertOne

Insert a single document

updateOne

Update a single document

deleteOne

Delete a single document

createIndex

Create a new index

dropIndex

Remove an index

indexes

List indexes for a collection