Heroku

by Heroku

v1.2.5

Apache-2.0

Repository Docs npm

Cloud & Infrastructure

herokudeploymentpaasdevops

Summary

Heroku's official MCP server — manage apps, dynos, add-ons, config, and logs from an AI client.

Features

List and manage apps, dynos, and add-ons
Read logs and run one-off commands
Manage config vars and Postgres databases

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "Heroku" tools will be available.

{
  "mcpServers": {
    "heroku": {
      "command": "npx",
      "args": [
        "-y",
        "@heroku/mcp-server"
      ],
      "env": {
        "HEROKU_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add heroku -e HEROKU_API_KEY=your-api-key -- npx -y @heroku/mcp-server

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "heroku": {
      "command": "npx",
      "args": [
        "-y",
        "@heroku/mcp-server"
      ],
      "env": {
        "HEROKU_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

{
  "command": "npx",
  "args": [
    "-y",
    "@heroku/mcp-server"
  ],
  "env": {
    "HEROKU_API_KEY": "your-api-key"
  }
}

Windsurf

{
  "command": "npx",
  "args": [
    "-y",
    "@heroku/mcp-server"
  ],
  "env": {
    "HEROKU_API_KEY": "your-api-key"
  }
}

VS Code

{
  "command": "npx",
  "args": [
    "-y",
    "@heroku/mcp-server"
  ],
  "env": {
    "HEROKU_API_KEY": "your-api-key"
  }
}

Description

Heroku's official MCP server lets an assistant operate a Heroku account through the platform API.

What it covers

Applications — list, inspect, create, and configure apps across teams and spaces
Dynos — scale, restart, and inspect process formations
Logs — read application and platform logs, which is what makes debugging a production issue conversational
Config vars — read and update environment configuration
Add-ons — provision, inspect, and manage attached services
Postgres — run queries, inspect database health, and manage backups
One-off commands — run a task dyno for migrations or maintenance scripts

Where it helps

The common operational loop — something is wrong, read the logs, check config, restart or scale, verify — collapses into a single conversation instead of a sequence of CLI invocations you half-remember.

Caution

The API key grants whatever your account can do, including scaling and destroying apps. Use a key scoped appropriately, and be specific about which app you are talking about.

Runs with npx -y @heroku/mcp-server.