Skip to main content
Glama
Sign In
mcp-permaudit

mcp-permaudit

by manueljacobo-nexgen
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

mcp-permaudit

Servidor MCP para auditar configuraciones de permisos de Claude Code (.claude/settings.json).

Aplica la jerarquía primitivas → custom → MCP:

  • cli_bash.py representa la opción primitiva (bash + Python).

  • audit.py encapsula la lógica para reutilizarla como tool custom.

  • server.py publica la capacidad como servidor MCP compartido.

Instalación

cd mcp-permaudit
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Related MCP server: SilentFail

Uso

Servidor MCP

source .venv/bin/activate
python server.py

Cliente de prueba

source .venv/bin/activate
python client_test.py

CLI primitiva

source .venv/bin/activate
python cli_bash.py fixtures/settings-destructive.json
python cli_bash.py /ruta/a/.claude/settings.json

Medir costo de contexto

source .venv/bin/activate
python measure_tokens.py

Configuración en clientes MCP

Claude Code

Copia o adapta .claude/mcp.json en tu proyecto o ~/.claude/mcp.json.

Claude Desktop

Copia claude_desktop_config.json como:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Actualiza la ruta absoluta a server.py.

Decisiones de diseño

Ver docs/decision.md para la comparación completa:

  • primitiva + ejecución de código

  • tool custom local

  • servidor MCP publicado

Incluye justificación de los cuatro criterios de MCP, costo de contexto medido, caso real reescrito como bash+Python, uso de MCP existente (Playwright MCP) y notas de seguridad/allowlist para producción.

Herramienta expuesta

  • audit_settings(settings_json: str) -> dict: audita el JSON de permisos y devuelve findings, summary, hasSettings, ruleCount y hasConflict.

Estructura

mcp-permaudit/
├── audit.py                    # Lógica pura de auditoría
├── server.py                   # Servidor MCP (FunctionTool + stdio)
├── client_test.py              # Cliente MCP de prueba
├── cli_bash.py                 # Alternativa primitiva
├── measure_tokens.py           # Costo de contexto
├── fixtures/                   # JSON de ejemplo
├── docs/decision.md            # Comparativa y justificación
├── .claude/mcp.json            # Config para Claude Code
├── claude_desktop_config.json  # Config para Claude Desktop
└── requirements.txt

This server cannot be deployed

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Resources

Related MCP Connectors

Related MCP Servers

  • mcpwatch

    lazymac2x
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that audits other MCP servers. Run MCPWatch security scans from inside Claude Code or any MCP-compatible agent with 10 OWASP MCP Top 10 aligned checks and A-F letter grades.
    MIT

  • SilentFail

    decksaga
    A
    license
    Not graded
    quality
    C
    maintenance
    Diagnose MCP servers — health checks, tool testing, token cost audits, conflict detection, and security scanning with 50+ prompt injection patterns. Works as CLI or MCP server inside Claude Desktop.
    1
    MIT
  • dr-mcp

    dr-mcpofficial

    Inferensys
    A
    license
    Not graded
    quality
    C
    maintenance
    Local-first MCP audit and cleanup tool that scans MCP configs to find stale servers, abandoned packages, duplicates, context-heavy tools, risky permissions, and major upgrades, generating reversible patch plans.
    44 npm
    MIT

  • whats-allowed-mcp

    stcmain
    A
    license
    A
    quality
    C
    maintenance
    Analyzes all permission settings files for coding agents, showing which settings take precedence and identifying rules that are accepted but ignored. Helps users understand and debug their agent's actual permission behavior.
    4
    64 npm
    1
    MIT