菜单
Validate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | mcp-check |
| description | Validate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check. |
| user-invocable | true |
Validate the project's MCP setup for correctness and completeness.
| File | Scope | What lives here |
|---|---|---|
.mcp.json (project root) | Project | mcpServers — the server definitions, written by claude mcp add --scope project |
.claude/settings.json | Project | Toggles only: enableAllProjectMcpServers, enabledMcpjsonServers |
~/.claude.json | User | User-scope mcpServers, available across all projects |
The source of truth for project servers is .mcp.json at the project root. Read mcpServers from there — .claude/settings.json never holds server definitions, only approval toggles.
.mcp.json is valid JSON (no trailing commas)mcpServers object exists in .mcp.json.claude/settings.json: either enableAllProjectMcpServers: true, or each server named in enabledMcpjsonServerscommand is validargs properly formattedenv variables set| MCP | Required? |
|---|---|
| memory | Recommended |
| filesystem | Optional |
| github | If .git exists |
## MCP Configuration Report
### Status: VALID / ISSUES / INVALID
### Configuration Summary
| MCP Server | Status | Notes |
|------------|--------|-------|
| memory | OK/FAIL | details |
### Issues Found
1. [Issue and fix]
### Missing Recommended MCPs
- memory: `claude mcp add --scope project memory...`
| Issue | Fix |
|---|---|
| Invalid JSON | Check trailing commas |
| MCP not loading | claude mcp reset-project-choices |
| Missing env vars | Add with -e KEY=value |
Guided 5-minute onboarding for Director Mode Lite. Use immediately after installing Director Mode Lite, or when unsure which command to run next.
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution
View Self-Evolving Loop session status, history, and memory metrics
Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient; routing decisions are made automatically based on task type, with no manual commands needed. Use when a task is a large refactor, a batch operation, or needs 100K+ tokens of context better handled by an external CLI.
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.