What are the prerequisites?
Python 3.13 (e.g., via `mise`) and `uv` (e.g., via Homebrew).
@ktrysmt
基本情報
A mcp server that executes shell scripts in a designated folder as tools.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-script-runner": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-script-runner",
"run",
"main.py"
]
}
}
}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。
MCP Script Runner is an MCP server that executes shell scripts as tools. It integrates with the Model Context Protocol and requires Python 3.13 and the uv package manager. The server is intended for developers who want to run local, trusted scripts through an MCP client.
Clone the repository, run uv sync to install dependencies, then add a JSON configuration to your MCP client. The configuration specifies the command as uv with arguments pointing to main.py. Optionally, set the COMMAND_DIRECTORY environment variable to change the working directory, or use a .env file for additional environment variables.
COMMAND_DIRECTORY env var../commands/.Python 3.13 (e.g., via `mise`) and `uv` (e.g., via Homebrew).
Create a shell script in the `./commands/` directory (e.g., `command_name.sh`) and reload the MCP server.
Each script must include a shebang, have execute permission (auto‑adjusted), and be intended for local use only. Only place scripts you fully understand.
Set the `COMMAND_DIRECTORY` environment variable in your MCP client’s configuration for the server entry.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
🚀 The fast, Pythonic way to build MCP servers and clients.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Model Context Protocol Servers
Hindsight: Agent Memory That Learns
コメント