What transport protocols does the server support?
The server supports both stdio (default) and SSE transport, configurable via command-line options.
@MyBlockcities
基本情報
概要はまだありません
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-server-heroku": {
"command": "docker",
"args": [
"compose",
"up",
"--build",
"-d"
]
}
}
}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。
A simple template for creating custom tools for Cursor IDE using Model Context Protocol (MCP). Users create their own repository from this template, modify the tools, and connect them to Cursor IDE.
Use the "Deploy to Heroku" button for quick deployment, or set up locally via Docker (docker compose up --build -d) or traditional Python setup with uv (uv run mcp-simple-tool). Connect to Cursor IDE by adding an MCP server in Settings → Features, using either SSE or stdio transport.
The server supports both stdio (default) and SSE transport, configurable via command-line options.
You can deploy to Heroku with a single click using the provided button, or run locally with Docker or Python.
In Cursor Settings → Features, add a new MCP server with Type set to "sse" (for Heroku/Docker) or "stdio" (for local run) and the appropriate URL or command path.
Available variables include MCP_SERVER_PORT, MCP_SERVER_HOST, DEBUG, and MCP_USER_AGENT.
The traditional setup requires Python and the uv package manager; Docker is optional but provides containerized deployment.
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.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
Open-source MCP server for Google Play developer workflows. Runs locally with your own credentials.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
コメント