MCP Database Server

A Model Context Protocol (MCP) server implementation that allows Large Language Models (LLMs) to interact with various databases through natural language. Currently supports MongoDB, with plans to support:

- PostgreSQL
- CockroachDB
- Redis
- And more...

- Database operations through natural language
- Currently supports MongoDB with features:

- List all collections
- Query documents with filtering and projection
- Insert documents
- Delete documents
- Aggregate pipeline operations

- PostgreSQL: SQL queries, table operations
- CockroachDB: Distributed SQL operations
- Redis: Key-value operations, caching

- Node.js v20.12.2 or higher
- Database (currently MongoDB, other databases coming soon)
- Claude Desktop Application

git clone https://github.com/manpreet2000/mcp-database-server.git cd mcp-database-server

To get started, you need to configure your database connection in your Claude Desktop configuration file:

~/Library/Application\ Support/Claude/claude_desktop_config.json

%APPDATA%/Claude/claude_desktop_config.json

Add the following configuration to yourclaude_desktop_config.json:

{ "mcpServers": { "database": { "command": "/path/to/node", "args": ["/path/to/mcp-database/dist/index.js"], "env": { "MONGODB_URI": "your-mongodb-connection-string" } } } }

- /path/to/nodewith your Node.js executable path or just usenode
- /path/to/mcp-databasewith the absolute path to this repository
- your-mongodb-connection-stringwith your MongoDB connection URL

Can you show me all the collections in my database?

Give me 2 records from the chargers collection

Show me all documents in the users collection where status is active

Add a new user to the users collection with name John and email john@example.com

Remove the user with email john@example.com from the users collection

Show me the total count of users by status in the users collection

Lists all collections in the connected database.

Retrieves documents from a collection with optional query parameters:

- collectionName: Name of the collection
- limit: Maximum number of documents to return (default: 10, max: 1000)
- query: MongoDB query object
- projection: Fields to include/exclude

Inserts a single document into a collection:

- collectionName: Name of the collection
- document: Document object to insert

Deletes a single document from a collection:

- collectionName: Name of the collection
- query: Query to match the document to delete

- collectionName: Name of the collection
- pipeline: Array of aggregation stages
- options: Optional aggregation options

- SQL query execution
- Table operations
- Schema management
- Transaction support

- Distributed SQL operations
- Multi-region support
- Transaction management
- Schema operations

- Key-value operations
- Caching mechanisms
- Pub/sub operations
- Data structure operations

- Never commit your database connection strings to version control
- Use environment variables for sensitive information
- Follow database-specific security best practices

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

Interact with AskTable SaaS or local deployments to query data sources using natural language.

Interact with MongoDB databases using natural language to query collections, inspect schemas, and manage data.

Interact with MongoDB databases using natural language. Query collections, inspect schemas, and manage data.

Provides read-only access to MongoDB databases through standardized MCP tools and resources.

AI-powered SQL query builder — natural language to SQL, schema introspection, query optimization, multi-dialect support by MEOK AI Labs

Terno is a database intelligence layer designed for security and accuracy, bridging the gap between AI agents and enterprise data. Connect instantly to the hosted server with OAuth — no installation required — or embed it directly into your own Django project.

Engram is a hosted MCP server that provides reliable memory for AI agents:

An MCP server that provides tools to interact with Powerdrill datasets, enabling smart AI data analysis and insights.

Multi-database agent access (PostgreSQL, SQLite, MySQL, Oracle, SQL Server) with batch queries, pre-configured connections, and SQLGlot-enforced read-only safety

An intelligent memory management server with 14 optimized tools. It provides AI-powered summaries, a clean interface, and supports an optional PostgreSQL database with pgvector.