# Wolfe Jam Faf MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.wolfe-jam%2Ffaf-mcp
Registry id: `mcp-registry/io.github.wolfe-jam/faf-mcp`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "wolfe-jam-faf-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "faf-mcp"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add wolfe-jam-faf-mcp-server -- npx -y faf-mcp
```

## Tools (15)

- `faf_about`: What the IANA-registered .faf format is, in plain language.
- `faf_agents`: Import AGENTS.md into project.faf, or write it from project.faf.
- `faf_auto`: One-call setup: init or merge, stack detection, CLAUDE.md, score.
- `faf_check`: Rate each human_context field empty / generic / good.
- `faf_claude`: Write CLAUDE.md from project.faf (all:true also writes other files).
- `faf_context`: Set or show the active project path.
- `faf_cursor`: Import .cursorrules into project.faf, or write it from project.faf.
- `faf_doctor`: Diagnose low score: missing files, slot counts, config issues.
- `faf_gemini`: Import GEMINI.md into project.faf, or write it from project.faf.
- `faf_git`: Author a project.faf from a public GitHub repo URL.
- `faf_go`: Guided interview to fill missing human-context and goal fields.
- `faf_init`: Create a new project.faf file.
- `faf_score`: AI-readiness score (0-100%) and tier; details:true adds breakdown.
- `faf_sync`: Reconcile project.faf with package.json (dry-run; apply:true writes).
- `faf_trust`: Validate required fields and about.* block with faf-cli validator.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.