{
  "markdown": "# Scout Monitoring MCP\n\n<a href=\"https://glama.ai/mcp/servers/@scoutapp/scout-mcp-local\">\n  <img width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/@scoutapp/scout-mcp-local/badge\" alt=\"Scout Monitoring MCP server\" />\n</a>\n\n[![MCP Badge](https://lobehub.com/badge/mcp/scoutapp-scout-mcp-local)](https://lobehub.com/mcp/scoutapp-scout-mcp-local)\n\n<hr\n\nThis repository contains code to locally run an MCP server that can access [Scout\nMonitoring](https://www.scoutapm.com) data via Scout's API. We provide a Docker image that can be pulled and run by\nyour AI Assistant to access Scout Monitoring data.\n\n\nThis puts Scout Monitoring's performance and error data directly in the hands of your AI Assistant.\nFor Rails, Django, FastAPI, Laravel and more. Use it to get traces and errors with line-of-code information\nthat the AI can use to target fixes right in your editor and codebase. N+1 queries, slow endpoints,\nslow queries, memory bloat, throughput issues - all your favorite performance problems surfaced\nand explained right where you are working.\n\n**If this makes your life a tiny bit better, why not :star: it?!**\n\n## Setup Wizard\n\nThe simplest way to configure and start using the Scout MCP is with our interactive setup wizard.\nIt handles all the prereqs and installation steps for you.\n\nRun via npx:\n```bash\nnpx @scout_apm/wizard\n```\n\nBuild and run from source:\n```bash\ncd ./wizard\nnpm install\nnpm run build\nnode dist/wizard.js\n```\n\nThe wizard will guide you through:\n- Selecting your AI coding platform (Cursor, Claude Code, Claude Desktop)\n- Entering your Scout API key\n- Automatically configuring the MCP server settings\n\n#### Supported Platforms\n\nThe wizard currently supports setup for:\n- **Cursor** - Automatically configures MCP settings\n- **Claude Code (CLI)** - Provides the correct command to run\n- **Claude Desktop** - Updates the configuration file for Windows/Mac\n\nFor all others, it will output JSON that you can copy/paste into your AI Assistant's MCP configuration.\n\n## Prerequisites\n\nThe Wizard is a great way to get started, but you can also set things up manually.\nYou will need to have or create a Scout Monitoring account and obtain an API key.\n\n1. [Sign\n   up](https://scoutapm.com/users/sign_up?utm_source=github&utm_medium=github&utm_campaign=scout-mcp-local)\n2. Install the Scout Agent in your application and send Scout data!\n    - [Ruby](https://scoutapm.com/docs/ruby/setup)\n    - [Python](https://scoutapm.com/docs/python/setup)\n    - [PHP](https://scoutapm.com/docs/php)\n    - If you are trying this out locally, make sure `monitor: true`, `errors_enabled: true`\n      are set in your config for the best experience\n2. Visit [settings](https://scoutapm.com/settings) to get or create an API key\n    - This is _not_ your \"Agent Key\"; it's the \"API Key\" that can be created on the\n      Settings page\n    - This is a read-only key that can only access data in your account\n2. Install Docker. Instructions below assume you can start a Docker container\n\n**The MCP server will not currently start without an API key set, either in the\nenvironment or by a command-line argument on startup.**\n\n## Installation\n\nWe recommend using the provided Docker image to run the MCP server.\nIt is intended to be started by your AI Assistant and configured with your Scout API\nkey. Many local clients allow specifying a command to run the MCP server in some\nlocation. A few examples are provided below.\n\nThe Docker image is available on [Docker Hub](https://hub.docker.com/r/scoutapp/scout-mcp-local).\n\nOf course, you can always clone this repo and run the MCP server directly; `uv` or other\nenvironment management tools are recommended.\n\n### Configure a local Client (e.g. Claude/Cursor/VS Code Copilot)\n\nIf you would like to configure the MCP manually, this usually just means supplying a command to run the MCP server with your API key in the environment\nto your AI Assistant's config. Here is the shape of the JSON (the top-level key varies):\n\n```json\n{\n  \"mcpServers\": {\n    \"scout-apm\": {\n      \"command\": \"docker\",\n      \"args\": [\"run\", \"--rm\", \"-i\", \"--env\", \"SCOUT_API_KEY\", \"scoutapp/scout-mcp-local\"],\n      \"env\": { \"SCOUT_API_KEY\": \"your_scout_api_key_here\"}\n    }\n  }\n}\n```\n\n<details>\n<summary> Claude Code</summary>\n\n```sh\nclaude mcp add scoutmcp -e SCOUT_API_KEY=your_scout_api_key_here -- docker run --rm -i -e SCOUT_API_KEY scoutapp/scout-mcp-local\n```\n</details>\n\n<details>\n<summary>Cursor</summary>\n\n[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=scout-apm&config=eyJjb21tYW5kIjoiZG9ja2VyIHJ1biAtLXJtIC1pIC0tZW52IFNDT1VUX0FQSV9LRVkgc2NvdXRhcHAvc2NvdXQtbWNwLWxvY2FsIiwiZW52Ijp7IlNDT1VUX0FQSV9LRVkiOiJ5b3VyX3Njb3V0X2FwaV9rZXlfaGVyZSJ9fQ%3D%3D)\n\nMAKE SURE to update the `SCOUT_API_KEY` value to your actual api key in\n  `Arguments` in the Cursor Settings > MCP\n</details>\n\n<details>\n<summary>VS Code Copilot</summary>\n\n- [VS Code Copilot docs](https://code.visualstudio.com/docs/copilot/customization/mcp-servers#_add-an-mcp-server)\n    - We recommend the \"Add an MCP server to your workspace\" option\n</details>\n\n<details>\n<summary>Claude Desktop</summary>\n\nAdd the following to your claude config file:\n- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n- **Windows**: `%APPDATA%/Claude/claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"scout-apm\": {\n      \"command\": \"docker\",\n      \"args\": [\"run\", \"--rm\", \"-i\", \"--env\", \"SCOUT_API_KEY\", \"scoutapp/scout-mcp-local\"],\n      \"env\": { \"SCOUT_API_KEY\": \"your_scout_api_key_here\"}\n    }\n  }\n}\n```\n\n</details>\n\n\n\n\n## Using the Scout Monitoring MCP\n\nScout's MCP is intended to put error and performance data directly in the... hands? of your AI Assistant.\nUse it to get traces and errors with line-of-code information that the AI can use to target\nfixes right in your editor.\n\nMost assistants will show you both raw tool calls and perform analysis. Desktop assistants\ncan readily create custom JS applications to explore whatever data you desire.\nAssistants integrated into code editors can use trace data and error backtraces to make\nfixes right in your codebase.\n\nCombine Scout's MCP with your AI Assistant's other tools to:\n\n- Create rich GitHub/GitLab issues based on errors and performance data\n- Make JIRA fun - have your AI Assistant create tickets with all the details\n- Generate PRs that fix specific errors and performance problems\n\n### Tools\n\nThe Scout MCP provides the following tools for accessing Scout APM data:\n\n- **`list_apps`** - List available Scout APM applications, with optional filtering by last active date\n- **`get_app_metrics`** - Get individual metric data (response_time, throughput, etc.) for a specific application\n- **`get_app_endpoints`** - Get all endpoints for an application with aggregated performance metrics\n- **`get_endpoint_metrics`** - Get timeseries metrics for a specific endpoint in an application\n- **`get_app_endpoint_traces`** - Get recent traces for an app filtered to a specific endpoint\n- **`get_app_trace`** - Get an individual trace with all spans and detailed execution information\n- **`get_app_error_groups`** - Get recent error groups for an app, optionally filtered by endpoint\n- **`get_app_insights`** - Get performance insights including N+1 queries, memory bloat, and slow queries\n\n### Resources\n\nThe Scout MCP provides configuration templates as resources that your AI assistant can read and apply:\n\n- **`scoutapm://config-resources/{framework}`** - Setup instructions for supported framework or library (rails, django, flask, fastapi)\n- **`scoutapm://config-resources/list`** - List all available configuration templates\n- **`scoutapm://metrics`** - List of all available metrics for Scout APM\n\n\n### Useful Prompts\n\n#### Setup & Configuration\n- \"Help me set up Scout monitoring for my Rails application\"\n- \"Create a Scout APM config file for my Django project with key ABC123\"\n\n#### Performance & Monitoring\n- \"Summarize the available tools in the Scout Monitoring MCP.\"\n- \"Find the slowest endpoints for app `my-app-name` in the last 7 days. Generate a table\n  with the results including the average response time, throughput, and P95 response time.\"\n- \"Show me the highest-frequency errors for app `Foo` in the last 24 hours. Get the\n  latest error detail, examine the backtrace and suggest a fix.\"\n- \"Get any recent n+1 insights for app `Bar`. Pull the specific trace by id and help me\n  optimize it based on the backtrace data.\"\n\n### Token Usage\n\nWe are currently more interested in expanding available information than strictly\ncontrolling response size from our MCP tools. If your AI Assistant has a configurable\ntoken limit (e.g. Claude Code `export MAX_MCP_OUTPUT_TOKENS=50000`), we recommend\nsetting it generously high, e.g. 50,000 tokens.\n\n## Local Development\n\nWe use `uv` and `taskipy` to manage environments and run tasks for this project.\n\n### Run with Inspector\n```bash\nuv run task dev\n```\nConnect within inspector to add API key, set to STDIO transport\n\n### Build the Docker image\n```bash\ndocker build -t scout-mcp-local .\n```\n\n## Release\n\n1. Branch and bump versions with `uv run python bump_versions.py`\n1. Get that merged\n1. Create a GitHub release with the new version (`gh release create v2025.11.3 --generate-notes --draft`)\n\nFor the bots:\n\nmcp-name: com.scoutapm/scout-mcp-local\n",
  "bytes": 9356,
  "sha": "f381b0918fde7b1a00dd0c2f5468b98ee491d9b4674f10b5848c0f5eb0dfd24a",
  "repo_slug": "scoutapp/scout-mcp-local",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_scoutapm_scout_mcp_local_caa624da/readme"
}