Scout Monitoring Mcp
@scoutapp
Scout Monitoring's local MCP server empowers AI Assistants by integrating application performance and error data directly into their workflows. It allows AI models to access traces, errors with line-of-code information, and performance insights like N+1 queries, slow endpoints, a
Overview
What is Scout Monitoring MCP?
Scout Monitoring MCP is a locally run MCP server that accesses Scout APM performance and error data via Scout’s API. It provides traces, errors, and line-of-code information to AI assistants for frameworks like Rails, Django, FastAPI, and Laravel.
How to use Scout Monitoring MCP?
Use the provided Docker image with your Scout API key. Configure the server in your AI assistant (Cursor, Claude Code, Claude Desktop, VS Code Copilot) by specifying a docker run command with the SCOUT_API_KEY environment variable. Alternatively, run the interactive setup wizard via npx @scout_apm/wizard to guide configuration. The server uses STDIO transport and requires Docker.
Key features of Scout Monitoring MCP
- Lists Scout APM applications with optional date filtering
- Retrieves aggregated endpoint metrics and timeseries data
- Fetches individual traces with full span details
- Shows error groups and performance insights (N+1 queries, memory bloat, slow queries)
- Provides configuration templates for supported frameworks as resources
- Integrates with AI coding platforms and editors
Use cases of Scout Monitoring MCP
- Surface slow endpoints and N+1 queries in a code editor and suggest fixes
- Analyze high‑frequency errors, examine backtraces, and generate fixes automatically
- Create rich GitHub/GitLab issues or JIRA tickets from performance data
- Generate pull requests that address specific errors and performance problems
FAQ from Scout Monitoring MCP
What are the prerequisites for using Scout Monitoring MCP?
You need a Scout Monitoring account, an API key (created on the Settings page, not the Agent Key), and Docker installed.
Does the server start without an API key?
No. The MCP server will not start without an API key set either in the environment or via a command‑line argument.
What platforms are supported for configuration?
Cursor, Claude Code (CLI), Claude Desktop, and VS Code Copilot are supported. A setup wizard automates configuration for these platforms.
Is there a recommended token limit for the AI assistant?
Yes. It is recommended to set a generous token limit for MCP output, e.g., MAX_MCP_OUTPUT_TOKENS=50000, since the tools can return large responses.
