You can use the MongoDB MCP server to get Performance Advisor recommendations from your preferred AI tools by using natural language. These recommendations include retrieving slow queries, performing index management, and suggesting schema improvements.
About the MongoDB MCP Server
The MongoDB MCP Server is a tool that allows you to interact with your MongoDB clusters in natural language by integrating with AI clients like Claude, Cursor, and GitHub Copilot.
To learn more about the MongoDB MCP Server, see What is the MongoDB MCP Server?.
Get Started
To quickly configure the MongoDB MCP Server for your AI client, complete the steps in Get Started with the MongoDB MCP Server.
To learn more about the performance advisor MCP tool, see Performance Advisor Tool.
For detailed examples with sample outputs, see Performance Optimization.
Considerations
When performing slow query analysis, the MCP Server retrieves a sample of slow queries, capped at 50 queries. The sample includes up to 50 most recent slow queries that match any specified conditions in your prompt to ensure optimal performance and response times.
This limitation does not apply to the Performance Advisor UI in Atlas.
Example Prompts
After you've configured the MongoDB MCP Server and connected it to your Atlas cluster, you can use natural language to retrieve Performance Advisor recommendations. The following table illustrates example prompts that you can use:
Use Case | Example Prompts | Performance Advisor Operation |
|---|---|---|
Analyze Slow Queries | Show me my slow queriesWhat is slowing down my cluster?Show me queries that are longer than 5 secondsShow me slow writes in the website.users namespace | |
Index Suggestions | Are there any indexes I should create to improve performance?What indexes do you recommend I drop? | |
Schema Advice | Show schema recommendations for my clusterHelp me optimize my database schema |