This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Sign in to like and favorite skills
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
jc-mcpvf activate jc-mcp# Activate virtual environment (Fish shell) vf activate jc-mcp # Start the FastAPI server locally uvicorn main:app --reload # Or run with Docker docker-compose up --build
# Activate virtual environment first vf activate jc-mcp # Run tests with pytest pytest # Run tests with verbose output and async support pytest -v
The server provides interactive API documentation at
http://localhost:8000/docsThis is a FastAPI-based MCP (Model Context Protocol) server for JumpCloud integration that provides:
/askmain.py: FastAPI application with REST endpoints and MCP protocol handlers
/askjumpcloud/client.py: JumpCloud API client
jumpcloud/mcp_agent_runner.py: Local agent for matching prompts to tools
jumpcloud/auth.py: API key authentication via x-api-key header
All endpoints require JumpCloud API key authentication via
x-api-keyJUMPCLOUD_API_KEYTools are registered in
TOOL_REGISTRYjumpcloud/mcp_agent_runner.pyRequired environment variables (set in
.envJUMPCLOUD_API_KEYMCP_API_URLCopy
.env.example.envThe
/askjumpcloud/mcp_agent_runner.pylist_systemsos: maclist_user_groupssearch_commandsThe agent uses simple keyword matching without requiring any external LLM services.
This server implements the Model Context Protocol and can be integrated with:
The MCP protocol exposes all JumpCloud tools for use within AI assistants and code editors.