Scout MCP Local - install, status & alternatives [2026]

01 · Install Scout MCP Local

before you install - you'll need

SCOUT_API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

claude mcp add scoutapp-scout-mcp-local -- uvx scout-mcp-local

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "scoutapp-scout-mcp-local": {
      "command": "uvx",
      "args": [
        "scout-mcp-local"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · container (OCI image) - can be sandboxed away from your filesystem

license MIT - declared in the repository

pypi package scout-mcp-local - check the name against the project README before installing (PyPI has no namespace ownership)

registry vendor namespace com.scoutapm - domain-verified with the official MCP registry

03 · What Scout MCP Local can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can 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, and get timeseries metrics for a specific endpoint in an application.

The 8 tools it gives your agent

Extracted from the project's README - what scout-mcp-local lets an agent do.

list_apps: - List available Scout APM applications, with optional filtering by last active date
get_app_metrics: - Get individual metric data (response_time, throughput, etc.) for a specific application
get_app_endpoints: - Get all endpoints for an application with aggregated performance metrics
get_endpoint_metrics: - Get timeseries metrics for a specific endpoint in an application
get_app_endpoint_traces: - Get recent traces for an app filtered to a specific endpoint
get_app_trace: - Get an individual trace with all spans and detailed execution information
get_app_error_groups: - Get recent error groups for an app, optionally filtered by endpoint
get_app_insights: - Get performance insights including N+1 queries, memory bloat, and slow queries

Latest releases

v2026.5.5 · 2026-05-05

Surface upstream HTTP status when body is not JSON · Fix get_app_metric arity mismatch (closes #73) · bump version to 2026.5.5

v2026.03.20 · 2026-03-25

add MCP server badge · Add glama.json · lobehub claim badge · Bump js-yaml from 4.1.0 to 4.1.1 in /wizard · Add background job support · Get usage tool · Bump minimatch in /wizard · Bump rollup from 4.52.3 to 4.59.0 in…

v2025.11.4 · 2025-11-04

Adjust MCP registry namespace

04 · Who maintains Scout MCP Local

scout-mcp-local is maintained by scoutapp. It's the only MCP server we track from this author; the repo dates to Aug 2025.

05 · Facts

repository: github.com/scoutapp/scout-mcp-local
category: DevOps & monitoring - ranked #53 of 101 actively-maintained DevOps & monitoring servers as of 2026-08-25.
registry: com.scoutapm/scout-mcp-local (active, first published 2025-11-04)
packages: pypi:scout-mcp-local · oci:docker.io/scoutapp/scout-mcp-local:latest

06 · Scout MCP Local FAQ

Is Scout MCP Local still maintained?

Yes - as of 2026-08-25, its last commit was 2026-06-20. We re-verify nightly.

What can Scout MCP Local do?

With this server connected, an agent can 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, and get timeseries metrics for a specific endpoint in an application.

How do I install Scout MCP Local?

Run `uvx scout-mcp-local`. The README documents one environment variable (SCOUT_API_KEY) to set first. You can also paste the ready-made client config above.

Does Scout MCP Local run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Scout MCP Local

Alternatives to Scout MCP Local

Maintained DevOps & monitoring servers if Scout MCP Local isn't the fit.

Pairs well with

Servers that cover what Scout MCP Local doesn't - only shown when the pairing reason fits the companion.

More DevOps & monitoring MCP servers · Better Stack MCP · Agentic Ledger · SigNoz MCP Server · HomeLab Monitor · Fleet MCP

More Python MCP servers · Scrape Badger · Social GPT · Fabric Dw · Sports Betting MCP · Glovebox MCP · see all