Scout Monitoring MCP Server

@scoutapp

Basic information

About Scout Monitoring MCP Server

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

#monitoring #apm #rails #django

Scout Monitoring MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "scout-apm": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--env",
        "SCOUT_API_KEY",
        "scoutapp/scout-mcp-local"
      ],
      "env": {
        "SCOUT_API_KEY": "your_scout_api_key_here"
      }
    }
  }
}

Scout Monitoring MCP Server tools

List available Scout APM applications, with optional filtering by last active date

Get individual metric data (response_time, throughput, etc.) for a specific application

Get all endpoints for an application with aggregated performance metrics

Get timeseries metrics for a specific endpoint in an application

Get recent traces for an app filtered to a specific endpoint

Get an individual trace with all spans and detailed execution information

Get recent error groups for an app, optionally filtered by endpoint

Get performance insights including N+1 queries, memory bloat, and slow queries

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

Frequently asked questions

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.

Comments

More Developer Tools MCP servers

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Official Porkbun MCP Server

Porkbun LLC

Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott