What are the runtime dependencies for Terminal MCP Server?
Node.js version 16 or higher and npm version 7 or higher are required.
@algae514
基本情報
概要はまだありません
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Terminal MCP Server is a Model Context Protocol (MCP) server implementation that allows AI assistants like Claude to execute terminal commands in specified directories. It is designed for users who need to grant an AI agent controlled command‑line access to their system.
Clone the repository, install dependencies with npm install, build with npm run build, and make start-server.sh executable. Then update your Claude configuration file to add the terminal MCP server entry, providing the absolute path to start-server.sh and the directories you want to expose.
Node.js version 16 or higher and npm version 7 or higher are required.
Add a `terminal` entry under `mcpServers` in your Claude configuration file, specifying the full path to `start-server.sh` as the command and the allowed directories as part of the server setup.
Directories where the server can run commands must be listed in a `maven-tool.json` file (a sample URL is provided in the repository). Only commands within those directories are permitted.
Use a dedicated user with limited permissions, be cautious about exposed directories, and review commands executed by Claude to ensure they are safe.
The project is licensed under the MIT License.

Free, public vulnerability feed for coding agents. One deduplicated entry per CVE, GHSA or OSV id, merged from the CVE List, GitHub Advisories, OSV, NVD, CISA KEV, EPSS and Exploit-DB. check_stack scans a lockfile for kn

Agent-Native Terminal


Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

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
コメント