What are the prerequisites to install MCP Terminal Server?
Windows operating system, Python 3.7 or higher, and administrator privileges (for service installation).
@cwmoore-ai
基本信息
A lightweight FastAPI server that can run as a Windows service and exposes an endpoint to execute shell commands and stream their output
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A lightweight FastAPI server that runs as a Windows service and exposes an endpoint to execute shell commands and stream their output in real-time. It includes API key authentication, rate limiting, and configurable logging.
Install via the provided PowerShell script (install_service.ps1) with optional parameters for API key, port, host, and log level. Configure through environment variables or a JSON config file. Manage the service using service.py commands (install, start, stop, restart, remove, debug). Use the test client (test_client.py) or call the API endpoints directly (POST /run, GET /health) with the API key in the X-API-Key header.
/health endpointWindows operating system, Python 3.7 or higher, and administrator privileges (for service installation).
Set the API key via the `-ApiKey` parameter during installation, the `MCP_TERMINAL_API_KEY` environment variable, or in the client configuration file (`client_config.json`).
Use debug mode by running `python service.py debug` from the terminal.
`POST /run` executes a command (requires API key, returns streaming output), and `GET /health` returns server health status.
The server blocks potentially dangerous commands, but additional security measures are recommended in production.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论