# Eval MCP

> Use for `/eval-mcp` requests that need the eval MCP handbook lookup.

- Skill: `getsentry/eval-mcp` (Agent Skill)
- Install (CLI): `npx skillmds@latest add getsentry/eval-mcp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/getsentry/eval-mcp/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Sentry (https://skillmd.com/u/getsentry)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/getsentry/eval-mcp

---


# Eval MCP Lookup

1. Always inspect the disclosed MCP tools and call the exact disclosed handbook search tool before answering.

2. Use the exact returned `mcp__eval-mcp__handbook-search` tool and pass the user's lookup request as `query` inside the tool `arguments` object. Never call the tool with only `tool_name`; use `tool_name: "mcp__eval-mcp__handbook-search", arguments: { "query": "<current lookup request>" }`.

3. Answer from the MCP result. Keep the final answer short.