ποΈ MongoDB MCP Server for LLMS
@QuantGeekDev
About ποΈ MongoDB MCP Server for LLMS
A mongo db server for the model context protocol (MCP)
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mongo-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"mongo-mcp",
"--client",
"claude"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is ποΈ MongoDB MCP Server for LLMS?
A Model Context Protocol (MCP) server that enables LLMs to interact directly with MongoDB databases. It allows querying collections, inspecting schemas, and managing data through natural language, designed for use with MCP clients such as the Claude Desktop app.
How to use ποΈ MongoDB MCP Server for LLMS?
Install via npx by adding the server configuration to your Claude Desktop config file (MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%/Claude/claude_desktop_config.json). The command uses npx mongo-mcp "mongodb://<username>:<password>@<host>:<port>/<database>?authSource=admin". Alternatively, install automatically via Smithery with npx -y @smithery/cli install mongo-mcp --client claude. Prerequisites: Node.js 18+ and npx. A local test sandbox can be set up using Docker Compose and the provided seed script.
Key features of ποΈ MongoDB MCP Server for LLMS
- Collection schema inspection
- Document querying with filtering and projection
- Index management (create, drop, list)
- Document operations (insert, update, delete)
Use cases of ποΈ MongoDB MCP Server for LLMS
- List available collections and inspect their schemas
- Find documents with complex filters (e.g., electronics under $1000)
- Create and manage indexes to optimize query performance
- Insert, update, or delete documents directly via natural language
- Query across collections using user references (e.g., orders by email)
FAQ from ποΈ MongoDB MCP Server for LLMS
What are the prerequisites for using this server?
Node.js 18+, npx, and an MCP client (e.g., Claude Desktop app). Docker and Docker Compose are needed only for the optional local test sandbox.
How do I connect to my existing MongoDB database?
Provide your MongoDB connection URL in the server configuration: mongodb://<username>:<password>@<host>:<port>/<database>?authSource=admin.
Can I test the server without a real MongoDB instance?
Yes. Use the provided Docker Compose file to start a local MongoDB and run npm run seed to populate sample data (Users, Products, Orders collections).
What tools does the server expose to the LLM?
Query tools: find, listCollections, insertOne, updateOne, deleteOne. Index tools: createIndex, dropIndex, indexes.
Where is the server configuration stored for Claude Desktop?
In claude_desktop_config.json located at ~/Library/Application Support/Claude/ on macOS or %APPDATA%/Claude/ on Windows.
More Databases MCP servers
ClickHouse MCP Server
ClickHouseConnect ClickHouse to your AI assistants.
Elasticsearch MCP Server
elasticMCP Server for Milvus
zilliztechModel Context Protocol Servers for Milvus
Sail MCP Server for Spark SQL
lakehqDrop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
Database Gateway
centralmindUniversal MCP-Server for your Databases optimized for LLMs and AI-Agents.
Comments