What prerequisites are needed?
Heroku CLI version 10.8.1 or higher must be installed globally on your system.
@heroku
基本情報
Heroku Platform MCP Server using the Heroku CLI
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": {
"heroku": {
"command": "npx",
"args": [
"-y",
"@heroku/mcp-server"
],
"env": {
"HEROKU_API_KEY": ""
}
}
}
}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。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
The Heroku Platform MCP Server is a Model Context Protocol (MCP) implementation that enables large language models (LLMs) to read, manage, and operate Heroku Platform resources through natural language. It works on Common Runtime, Cedar Private and Shield Spaces, and Fir Private Spaces, and is intended for developers and teams who want to interact with Heroku via conversational AI.
Install the Heroku CLI (version 10.8.1 or higher). Then launch the server either with heroku mcp:start (recommended, uses existing CLI authentication) or with npx -y @heroku/mcp-server after setting the HEROKU_API_KEY environment variable. Configure your MCP client (Claude Desktop, Zed, Cursor, Windsurf, Cline, VS Code, or Trae) with one of the provided command examples.
Heroku CLI version 10.8.1 or higher must be installed globally on your system.
You can use `heroku mcp:start` to authenticate with your existing Heroku CLI session, or set the `HEROKU_API_KEY` environment variable with a Heroku authorization token when using `npx -y @heroku/mcp-server`.
Claude Desktop, Zed, Cursor, Windsurf, Cline, VS Code, and Trae are explicitly supported with configuration examples in the README.
The server works on Common Runtime, Cedar Private and Shield Spaces, and Fir Private Spaces.
It is currently in early development; functionality and available tools may evolve.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
Open-source MCP to use Blender with any LLM
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
コメント