TOOLS
MongoDB MCP Server
The MongoDB MCP Server gives AI agents the tools they need to explore, query, and manage MongoDB deployments. Run it self-managed locally, or use the Atlas Managed MCP Server.
Ship better software, faster
Automatically surface critical database context, including configurations, collection schemas, and sample data, directly to your coding agents. They’ll write more accurate MongoDB code and optimized queries while you stay in the flow.
_Spot.svg)
Simplify development workflows
No more copy-pasting schemas or switching tools. Explore, code, and manage MongoDB deployments without leaving your development environment.
_Spot_(1).svg)
Power your own agents
The MongoDB MCP Server acts as a standard plugin for any MCP-enabled environment. Build autonomous agents that can explore datasets, generate insights, and interact with MongoDB deployments.
Connecting the MongoDB MCP Server to your AI development tools lets you use natural language to explore and manage databases while generating accurate application code.
View our AI plugins and connectors
The best way to access your data and manage your databases in your favorite AI tools.
ChatGPT
ChatGPT App for MongoDB Atlas for accessing data and managing the platform.
Codex
MongoDB Atlas (Managed MCP) and MongoDB (Self-Managed MCP) plugins for querying data and managing databases in Codex.
.svg){kind=logo}
Claude
Connector for MongoDB Atlas, enabling accessing your data and managing the platform from Claude.
Claude Code
MongoDB Atlas (Managed MCP) and MongoDB (Self-Managed MCP) plugins for querying data and managing databases in Claude Code.
.svg){kind=logo}
.svg){kind=logo}
.svg)
Interact with your data in natural language
Explore and manage databases using natural language directly in your development environment to build faster and more easily.
Ship software faster
The MongoDB MCP Server enables coding agents to query and manage data, helping them iterate faster and build application features more reliably.
Power agentic systems
Integrate the MongoDB MCP Server with your agentic systems so they can explore and query MongoDB deployments effectively.
Learning hub
Quick and easy resources to start building with the MongoDB MCP Server.
FAQ
An MCP server implements the Model Context Protocol (MCP), introduced by Anthropic in November 2024. MCP is a standard that defines how LLM-based applications connect with diverse data sources and systems, especially for agentic use cases. It enables interoperability and modularity in complex AI ecosystems, making deployment easier, more flexible, and scalable.
The MongoDB MCP Server connects any MongoDB deployment (Atlas, Community Edition, or Enterprise Advanced) to AI-powered developer tools like Codex, Claude, or any MCP-enabled agentic system. It brings context from MongoDB databases into developers’ environments, enabling data exploration, database operations, and context-aware code generation via natural language.
Additionally, the MongoDB MCP Server can serve as a building block for AI agents, giving them direct access to MongoDB databases for data retrieval and automated database operations.
The MongoDB MCP Server can be installed locally and self-managed or you can use the Atlas Managed MCP Server.
Yes. The MongoDB MCP Server works with any MongoDB deployment, including Community Edition, Enterprise Advanced, and Atlas.
You can deploy the MongoDB MCP Server locally using stdio (for IDEs/agents like Claude Code or Cursor) or HTTP. It can also be self-hosted for broader access or packaged and deployed with Docker for easier containerized setups. In addition, for a fully hosted MCP Server, use the Atlas Managed MCP Server.
Get started with the MongoDB MCP Server
- Ship better software, faster
- Works with your favorite AI tools
- Simplified development workflows