mcpField
M
MCP Database Server

MCP Database Server

Local
github.com/manpreet2000Databases0Updated 83w ago

About MCP Database Server

MCP Database Server lets LLMs operate databases through natural language, with MongoDB currently supported. It provides tools for browsing collections, querying and changing documents, and running aggregation pipelines.

Key features

  1. 01List MongoDB collections
  2. 02Filter and project documents
  3. 03Insert and delete documents
  4. 04Run aggregation pipelines

Use cases

  1. 01Inspect collections in a database
  2. 02Find documents by criteria
  3. 03Add or remove collection records
  4. 04Aggregate and analyze collection data

MCP support

As an MCP server, it exposes MongoDB collection, document query and mutation, and aggregation tools to clients. MongoDB is currently supported; other databases are planned.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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...

Features

  • 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
  • Future support for other databases:
    • PostgreSQL: SQL queries, table operations
    • CockroachDB: Distributed SQL operations
    • Redis: Key-value operations, caching

Prerequisites

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

Installation

  1. Clone the repository:
git clone https://github.com/manpreet2000/mcp-database-server.git
cd mcp-database-server
  1. Install dependencies:
npm install
  1. Build the TypeScript code:
npm run build

Configuration

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

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

Add the following configuration to your claude_desktop_config.json:

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

Replace:

  • /path/to/node with your Node.js executable path or just use node
  • /path/to/mcp-database with the absolute path to this repository
  • your-mongodb-connection-string with your MongoDB connection URL

Usage Examples

MongoDB Examples
  1. List all collections in your database:
Can you show me all the collections in my database?
  1. Get specific records from a collection:
Give me 2 records from the chargers collection
  1. Query with filters:
Show me all documents in the users collection where status is active
  1. Insert a document:
Add a new user to the users collection with name John and email [email protected]
  1. Delete a document:
Remove the user with email [email protected] from the users collection
  1. Aggregate data:
Show me the total count of users by status in the users collection

Available Tools

1. getCollections

Lists all collections in the connected database.

2. getCollection

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
3. insertOne

Inserts a single document into a collection:

  • collectionName: Name of the collection
  • document: Document object to insert
4. deleteOne

Deletes a single document from a collection:

  • collectionName: Name of the collection
  • query: Query to match the document to delete
5. aggregate

Executes an aggregation pipeline:

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

Future Database Support

PostgreSQL
  • SQL query execution
  • Table operations
  • Schema management
  • Transaction support
CockroachDB
  • Distributed SQL operations
  • Multi-region support
  • Transaction management
  • Schema operations
Redis
  • Key-value operations
  • Caching mechanisms
  • Pub/sub operations
  • Data structure operations

Security

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

Contributing

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.

License

MIT License - See LICENSE for details

Comments

Markdown supported

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.