mcp-permaudit
Audits Claude Code permission settings (.claude/settings.json) via an MCP tool, detecting conflicts and misconfigurations.
README
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.txt
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.