MongoDB MCP Server

MongoDB MCP Server

A Model Context Protocol (MCP) server for MongoDB operations, enabling AI assistants to interact with MongoDB databases through a standardized interface.

Category
Visit Server

README

MongoDB MCP Server

A Model Context Protocol (MCP) server for MongoDB operations, enabling AI assistants to interact with MongoDB databases through a standardized interface.

Features

Core Operations

  • Database Operations: List, stats, drop databases
  • Collection Operations: Create, drop, rename, list collections
  • Document Operations: Full CRUD (find, insert, update, delete), aggregation
  • Index Operations: Create, list, drop indexes

Security & Access Control

  • Permission System: Role-based access control with allowed/denied databases and collections
  • Read-Only Mode: Prevent all write operations
  • Query Result Limits: Configurable maximum results per query
  • Bulk Operation Limits: Control maximum bulk operations

Monitoring & Auditing

  • Audit Logging: Track all operations with timestamps, success/failure status
  • Rate Limiting: Prevent abuse with configurable request limits
  • Health Check: Monitor MongoDB connection and server status

Data Protection

  • Data Masking: Automatically mask sensitive fields (passwords, tokens, etc.)
  • Confirmation Prompts: Require confirmation for dangerous operations (drop database/collection)

Configuration

  • Configuration File: Support for JSON configuration files
  • Environment Variables: All settings configurable via environment variables
  • Connection Pooling: MongoDB driver connection pooling

Installation

npm install mongodb-mcp

Or from source:

git clone https://github.com/az-coder-123/mongodb-mcp.git
cd mongodb-mcp
npm install
npm run build

Configuration

Configuration File

Create a mcp-settings.json file in your project root or home directory:

{
  "connectionString": "mongodb://localhost:27017",
  "permissions": {
    "readOnly": false,
    "allowedDatabases": ["myapp", "analytics"],
    "deniedDatabases": ["admin", "config"],
    "allowedCollections": {
      "myapp": ["users", "orders", "products"]
    },
    "deniedTools": ["drop_database"],
    "maxQueryResults": 1000,
    "maxBulkOperations": 1000
  },
  "auditLog": {
    "enabled": true,
    "logFilePath": "./logs/audit.log",
    "maxEntries": 10000,
    "logSuccess": true,
    "logFailure": true
  },
  "rateLimit": {
    "enabled": true,
    "maxRequests": 100,
    "windowMs": 60000
  },
  "dataMasking": true,
  "maskedFields": ["password", "secret", "token", "apiKey"]
}

Environment Variables

Variable Description Default
MONGODB_URI MongoDB connection string mongodb://localhost:27017
MCP_READ_ONLY Enable read-only mode false
MCP_ALLOWED_DATABASES Comma-separated list of allowed databases (all allowed)
MCP_DENIED_DATABASES Comma-separated list of denied databases (none)
MCP_DENIED_TOOLS Comma-separated list of denied tools (none)
MCP_MAX_QUERY_RESULTS Maximum query results 1000
MCP_MAX_BULK_OPERATIONS Maximum bulk operations 1000
MCP_AUDIT_LOG_ENABLED Enable audit logging true
MCP_AUDIT_LOG_PATH Audit log file path (console only)
MCP_RATE_LIMIT_ENABLED Enable rate limiting true
MCP_RATE_LIMIT_MAX_REQUESTS Max requests per window 100
MCP_RATE_LIMIT_WINDOW_MS Rate limit window (ms) 60000
MCP_DATA_MASKING_ENABLED Enable data masking true
MCP_MASKED_FIELDS Comma-separated masked fields password,secret,token,apiKey

Usage with Claude Desktop

Add to your Claude Desktop configuration:

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

{
  "mcpServers": {
    "mongodb": {
      "command": "node",
      "args": ["/path/to/mongodb-mcp/dist/index.js"],
      "env": {
        "MONGODB_URI": "mongodb://localhost:27017"
      }
    }
  }
}

Available Tools

Database Operations

list_databases

List all databases in the MongoDB instance.

{}

database_stats

Get statistics for a specific database.

{
  "database": "mydb"
}

drop_database

⚠️ Drop a database (requires confirmation).

{
  "database": "test_db",
  "confirm": true
}

Collection Operations

list_collections

List all collections in a database.

{
  "database": "mydb"
}

create_collection

Create a new collection.

{
  "database": "mydb",
  "collection": "users",
  "options": {
    "capped": true,
    "size": 1048576,
    "max": 1000
  }
}

drop_collection

⚠️ Drop a collection (requires confirmation).

{
  "database": "mydb",
  "collection": "temp_data",
  "confirm": true
}

Document Operations

find

Find documents with filters, projections, sorting, and pagination.

{
  "database": "mydb",
  "collection": "users",
  "filter": { "age": { "$gte": 18 } },
  "projection": { "name": 1, "email": 1 },
  "sort": { "name": 1 },
  "limit": 10,
  "skip": 0
}

insert_one

Insert a single document.

{
  "database": "mydb",
  "collection": "users",
  "document": {
    "name": "John Doe",
    "email": "john@example.com",
    "age": 30
  }
}

insert_many

Insert multiple documents.

{
  "database": "mydb",
  "collection": "users",
  "documents": [
    { "name": "User 1", "email": "user1@example.com" },
    { "name": "User 2", "email": "user2@example.com" }
  ]
}

update_one

Update a single document.

{
  "database": "mydb",
  "collection": "users",
  "filter": { "email": "john@example.com" },
  "update": { "$set": { "age": 31 } },
  "upsert": false
}

delete_one

Delete a single document.

{
  "database": "mydb",
  "collection": "users",
  "filter": { "email": "john@example.com" }
}

aggregate

Run an aggregation pipeline.

{
  "database": "mydb",
  "collection": "orders",
  "pipeline": [
    { "$match": { "status": "completed" } },
    { "$group": { "_id": "$customerId", "total": { "$sum": "$amount" } } },
    { "$sort": { "total": -1 } },
    { "$limit": 10 }
  ]
}

Index Operations

create_index

Create an index on a collection.

{
  "database": "mydb",
  "collection": "users",
  "keys": { "email": 1 },
  "options": {
    "unique": true,
    "name": "email_unique_idx"
  }
}

Monitoring Tools

health_check

Check MongoDB connection health and server status.

{}

get_audit_log

Get audit log entries.

{
  "limit": 100,
  "toolName": "insert_one",
  "failuresOnly": false
}

get_server_config

Get current server configuration.

{}

set_read_only

Enable or disable read-only mode.

{
  "enabled": true
}

Security Features

Permission System

Control access to databases and collections:

{
  "permissions": {
    "allowedDatabases": ["myapp"],
    "deniedDatabases": ["admin"],
    "allowedCollections": {
      "myapp": ["users", "orders"]
    },
    "deniedTools": ["drop_database", "drop_collection"]
  }
}

Read-Only Mode

Prevent all write operations:

MCP_READ_ONLY=true node dist/index.js

Or via tool call:

{
  "name": "set_read_only",
  "arguments": { "enabled": true }
}

Confirmation Prompts

Dangerous operations require explicit confirmation:

  • drop_database requires "confirm": true
  • drop_collection requires "confirm": true

Data Masking

Sensitive fields are automatically masked in responses:

{
  "dataMasking": true,
  "maskedFields": ["password", "secret", "token", "apiKey", "creditCard"]
}

Rate Limiting

Prevent abuse with configurable limits:

{
  "rateLimit": {
    "enabled": true,
    "maxRequests": 100,
    "windowMs": 60000
  }
}

Error Handling

The server implements a comprehensive error handling system with structured error classes, automatic categorization, and actionable recovery suggestions.

Error Format

The server returns errors in the following format:

{
  "content": [
    {
      "type": "text",
      "text": "VALIDATION_ERROR: Invalid value for 'collection': expected string, got number\n\nSuggestions:\n  1. Check 'collection' parameter\n  2. Refer to documentation for valid values\n\nContext: {\n  \"field\": \"collection\",\n  \"value\": 123,\n  \"expectedType\": \"string\"\n}"
    }
  ],
  "isError": true
}

Error Categories

All errors are categorized for proper handling:

Category Description
VALIDATION Invalid input parameters
PERMISSION Access denied
RATE_LIMIT Too many requests
CONNECTION MongoDB connection issues
OPERATION Database operation failures
NOT_FOUND Resource not found
CONFIGURATION Invalid configuration

Error Types

The server provides specific error types with recovery suggestions:

  • ValidationError - Input validation errors
  • PermissionError - Access denied errors
  • RateLimitError - Rate limit exceeded
  • ConnectionError - MongoDB connection failures
  • OperationError - Database operation failures
  • NotFoundError - Resource not found
  • ConfigurationError - Configuration errors
  • ReadOnlyError - Read-only mode violations
  • BulkLimitError - Bulk operation limits
  • QueryLimitError - Query result limits
  • ConfirmationRequiredError - Dangerous operations without confirmation

Documentation

For comprehensive error handling documentation, see docs/error-handling.md.

This guide includes:

  • Complete error classes reference
  • Error handling utilities
  • Best practices
  • Error recovery patterns
  • Common troubleshooting scenarios

Development

Running in development mode

npm run dev

This will watch for file changes and automatically rebuild.

Building

npm run build

Cleaning

npm run clean

Architecture

src/
├── types/
│   └── index.ts          # TypeScript interfaces and types
├── validators/
│   └── index.ts          # Input validation functions
├── handlers/
│   ├── database.ts       # Database operation handlers
│   ├── collection.ts     # Collection operation handlers
│   ├── document.ts       # Document CRUD handlers
│   ├── index-operations.ts # Index operation handlers
│   └── index.ts          # Handler exports
├── resources/
│   └── index.ts          # MCP resource handlers
├── tools/
│   └── index.ts          # Tool definitions
├── utils/
│   ├── permission-checker.ts  # Permission system
│   ├── audit-logger.ts        # Audit logging
│   ├── rate-limiter.ts        # Rate limiting
│   ├── data-masker.ts         # Data masking
│   ├── config-loader.ts       # Configuration loading
│   └── index.ts               # Utility exports
├── server.ts             # Main server class
└── index.ts              # Entry point

License

MIT License - see LICENSE file for details.

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured