mcp-permaudit
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-permaudit
Servidor MCP para auditar configuraciones de permisos de Claude Code
(.claude/settings.json).
Aplica la jerarquía primitivas → custom → MCP:
cli_bash.pyrepresenta la opción primitiva (bash + Python).audit.pyencapsula la lógica para reutilizarla como tool custom.server.pypublica la capacidad como servidor MCP compartido.
Instalación
cd mcp-permaudit
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtRelated MCP server: SilentFail
Uso
Servidor MCP
source .venv/bin/activate
python server.pyCliente de prueba
source .venv/bin/activate
python client_test.pyCLI primitiva
source .venv/bin/activate
python cli_bash.py fixtures/settings-destructive.json
python cli_bash.py /ruta/a/.claude/settings.jsonMedir costo de contexto
source .venv/bin/activate
python measure_tokens.pyConfiguración 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.jsonWindows:
%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.txtTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.
Free MCP contract auditing for AI agents and developers. Check tool schemas, detect potential breaking changes between versions, and get structured compatibility findings before deployment. Static analysis only.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP 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
- AlicenseNot gradedqualityDmaintenanceDiagnose 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.1MIT
- AlicenseAqualityCmaintenanceAnalyzes 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.455 npm1MIT
- AlicenseNot gradedqualityCmaintenanceEnables any MCP client to detect Claude Code configuration that is silently ignored, such as agent files that fail to load, unknown frontmatter fields, parent-folder settings, conflicting MCP server entries and drift since a baseline. Exposes read-only tools that return findings with exact edits, the fix prompt, and explanations of each check, without modifying any files.Apache 2.0