About MongoDB MCP Server
MongoDB MCP Server provides read-only tools and resources for AI assistants to explore and analyze MongoDB databases. It combines querying, aggregation, schema discovery, and data inspection while preventing write operations.
Key features
- 01List databases and collections
- 02Infer schemas from sample documents
- 03Filter, sort, and project query results
- 04Run validated read-only aggregation pipelines
- 05Search text and geospatial data
- 06Inspect statistics, indexes, and query plans
Use cases
- 01Explore database structure and collection fields
- 02Analyze data with queries and aggregations
- 03Inspect query plans and collection performance
MCP support
The MCP server exposes read-only MongoDB operations as standardized tools and resources for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMongoDB MCP Server
A Model Context Protocol server that provides read-only access to MongoDB databases through standardized MCP tools and resources.
Overview
This MongoDB MCP server enables AI assistants to directly query and analyze MongoDB databases without write access, maintaining data safety while providing powerful data exploration capabilities.
Features
MongoDB Operations
- Database Exploration: List databases and collections
- Schema Discovery: Infer collection schemas from sample documents
- Querying: Execute MongoDB queries with filtering, projection, sorting, and limiting
- Aggregation: Run read-only aggregation pipelines with safety validation
- Text Search: Perform full-text search on collections with text indexes
- Geospatial Queries: Find locations near points, within polygons, or intersecting geometries
- Document Operations: Count documents, sample random documents, find documents by IDs
- Data Analysis: Get collection statistics, index information, and query execution plans
- Performance Insights: Examine query execution plans to optimize performance
- Data Exploration: Get distinct values, field distributions, and data samples
- Format Conversion: Export query results as JSON or CSV formats
Enhanced Capabilities
- Schema Inference: Automatically detect data types and structure from documents
- Visualization Hints: Intelligent suggestions for data visualization based on result content
- Safety Validation: Prevents write operations in aggregation pipelines
- Example-Rich Documentation: Each tool includes detailed examples in its description
Requirements
Environment Variables
MONGODB_URI(required): MongoDB connection string with authentication if neededMONGODB_DEFAULT_DATABASE(optional): Default database name when not specified in queries
Prerequisites
- Network access to MongoDB server
- Authentication credentials if required by MongoDB instance
- Appropriate read permissions on target databases
Installation
Building from Source
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Integration with Claude Desktop
To use with Claude Desktop, add the server configuration:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mongodb": {
"command": "/path/to/mongodb-server/build/index.js",
"env": {
"MONGODB_URI": "mongodb://username:password@hostname:port/database",
"MONGODB_DEFAULT_DATABASE": "your_default_db"
}
}
}
}
Integration with Claude Web
For Claude Web via the MCP Chrome extension, add configuration to Cline MCP settings:
{
"mcpServers": {
"mongodb": {
"command": "node",
"args": ["/path/to/mongodb-server/build/index.js"],
"env": {
"MONGODB_URI": "mongodb://username:password@hostname:port/database",
"MONGODB_DEFAULT_DATABASE": "your_default_db"
}
}
}
}
Integration with Claude Code
To use with Claude Code, use the following commands:
cd /path/to/my/project
claude mcp add mongo-server /path/to/mongodb-mcp/build/index.js -e "MONGODB_URI=mongodb://user@password:27017/dbname?authSource=authDbName" -e MONGO_DEFAULT_DATABASE=dbname
Make sure to replace the placeholders with your actual MongoDB connection string and default database name.
If configured correctly, you should see the following when you run claude:
╭───────────────────────────────────────────────────────╮
│ ✻ Welcome to Claude Code research preview! │
│ │
│ /help for help │
│ │
│ cwd: <path-to-project-directory> │
│ │
│ ─────────────────────────────────────────────────── │
│ │
│ MCP Servers: │
│ │
│ • mongo-server connected │
╰───────────────────────────────────────────────────────╯
If you run into issues, see the Claude Code documentation.
Security Considerations
- This server provides read-only access by design
- Connection strings may contain sensitive authentication information
- Store connection strings securely in environment variables
- Use a MongoDB user with read-only permissions
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.