Heroku Platform MCP Server
Last updated April 22, 2025
Table of Contents
The Heroku Platform MCP Server is currently in early development. As we continue to enhance and refine the implementation, the available functionality and tools may evolve. We welcome feedback and contributions to help shape the future of this project.
The Heroku Platform MCP Server is a specialized Model Context Protocol (MCP) implementation designed to facilitate interaction between large language models (LLMs) and the Heroku Platform. This server provides a robust set of tools and capabilities that enable LLMs to read, manage, and operate Heroku Platform resources. With this implementation, AI-powered applications like Claude Desktop, Cursor, and Windsurf can directly interface with Heroku.
Use Cases and Benefits
You can use the Heroku MCP Server to improve various core developer workflows:
- App lifecycle management: Empower agents to handle deploying, scaling, restarting, viewing logs, and monitoring your applications.
- Database operations: Enable actions on your Heroku Postgres databases.
- Add-on management: Enable agents to discover available add-ons and attach or detach resources to your apps.
- Scaling and performance: Facilitate intelligent scaling of your application resources.
The Heroku MCP Server is open-source and available on GitHub.
The Heroku MCP Server works on Common Runtime, Cedar Private and Shield Spaces, and Fir Private Spaces.
How It Works
The Heroku MCP Server uses the Heroku CLI to execute actions. To maximize performance and responsiveness, the server runs the Heroku CLI in Read-Eval-Print Loop (REPL) mode. This enables faster command execution and more efficient multitool operations as it doesn’t require launching a new CLI process for each action.
Authentication
Generate a Heroku authorization token with one of these methods:
- Use the Heroku CLI command:
heroku authorizations:create
- Use an existing token in the CLI
heroku auth:token
- Use your Heroku Dashboard:
- Click your avatar, then select
Account Settings
. - Open the
Applications
tab. - Next to
Authorizations
, clickCreate authorization
.
- Click your avatar, then select
Copy the token and use it as your HEROKU_API_KEY
to configure the Heroku MCP Server.
Configure the Heroku MCP Server
You can configure Claude Desktop, Zed, Cursor, and Windsurf to work with the Heroku MCP Server.
Claude Desktop
Add this snippet to your claude_desktop_config.json
:
{
"mcpServers": {
"heroku": {
"command": "npx -y @heroku/mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
}
Zed
Add this snippet to your Zed settings.json
:
{
"context_servers": {
"heroku": {
"command": {
"path": "npx",
"args": ["-y", "@heroku/mcp-server"],
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
}
}
Cursor
Add this snippet to your Cursor mcp.json
:
{
"mcpServers": {
"heroku": {
"command": "npx -y @heroku/mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
}
Windsurf
Add this snippet to your Windsurf mcp_config.json
:
{
"mcpServers": {
"heroku": {
"command": "npx -y @heroku/mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
}
Available Tools
Application Management
list_apps
- List all Heroku apps. You can filter apps by personal, collaborator, team, or space.get_app_info
- Get detailed information about an app, including its configuration, dynos, and add-ons.create_app
- Create a new app with customizable settings for region, team, and space.rename_app
- Rename an existing app.transfer_app
- Transfer ownership of an app to another user or team.deploy_to_heroku
- Deploy projects to Heroku with anapp.json
configuration, supporting team deployments, spaces, and environment setups.deploy_one_off_dyno
- Execute code or commands in a sandboxed environment on a Heroku one-off dyno. Supports file creation, network access, environment variables, and automatic cleanup. Ideal for running scripts, tests, or temporary workloads.
Process & Dyno Management
ps_list
- List all dynos for an app.ps_scale
- Scale the number of dynos up or down, or resize dynos.ps_restart
- Restart specific dynos, process types, or all dynos.
Add-ons
list_addons
- List all add-ons for all apps or for a specific app.get_addon_info
- Get detailed information about a specific add-on.create_addon
- Provision a new add-on for an app.
Maintenance & Logs
maintenance_on
- Enable maintenance mode for an app.maintenance_off
- Disable maintenance mode for an app.get_app_logs
- View application logs.
Pipeline Management
pipelines_create
- Create a new pipeline.pipelines_promote
- Promote apps to the next stage in a pipeline.pipelines_list
- List available pipelines.pipelines_info
- Get detailed pipeline information.
Team & Space Management
list_teams
- List teams you belong to.list_private_spaces
- List available spaces.
PostgreSQL Database Management
pg_psql
- Execute SQL queries against the Heroku PostgreSQL database.pg_info
- Display detailed database information.pg_ps
- View active queries and execution details.pg_locks
- View database locks and identify blocking transactions.pg_outliers
- Identify resource-intensive queries.pg_credentials
- Manage database credentials and access.pg_kill
- Terminate specific database processes.pg_maintenance
- Show database maintenance information.pg_backups
- Manage database backups and schedules.pg_upgrade
- Upgrade PostgreSQL to a newer version.
Debugging
You can use the MCP inspector or the VS Code Run and Debug function to run and debug the server.
- Link the project as a global CLI using
npm link
from the project root. - Build with
npm run build:dev
or watch for file changes and build automatically withnpm run build:watch
.
Use the MCP Inspector
Use the MCP inspector with no breakpoints in the code:
# Breakpoints are not available
npx @modelcontextprotocol/inspector heroku-mcp-server
Alternatively, if you installed the package in a specific directory or are actively developing on the Heroku MCP server:
cd /path/to/servers
npx @modelcontextprotocol/inspector dist/index.js
Use the VS Code Run and Debug Function
Use the VS Code Run and Debug launcher with fully functional breakpoints in the code:
- Locate and select the run debug.
- Select the configuration labeled
MCP Server Launcher
in the dropdown. - Select the
Run/Debug
button.
VS Code / Cursor Debugging Setup
To set up local debugging with breakpoints:
Store your Heroku auth token in the VS Code user settings:
- Open the
Command Palette
withCmd/Ctrl
+Shift
+P
. - Type
Preferences: Open User Settings (JSON)
. - Add this snippet:
json { "heroku.mcp.authToken": "your-token-here" }
- Open the
Create or update
.vscode/launch.json
:{ "version": "0.2.0", "configurations": [ { "type": "node", "request": "launch", "name": "MCP Server Launcher", "skipFiles": ["<node_internals>/**"], "program": "${workspaceFolder}/node_modules/@modelcontextprotocol/inspector/bin/cli.js", "outFiles": ["${workspaceFolder}/**/dist/**/*.js"], "env": { "HEROKU_API_KEY": "${config:heroku.mcp.authToken}", "DEBUG": "true" }, "args": ["heroku-mcp-server"], "sourceMaps": true, "console": "integratedTerminal", "internalConsoleOptions": "neverOpen", "preLaunchTask": "npm: build:watch" }, { "type": "node", "request": "attach", "name": "Attach to Debug Hook Process", "port": 9332, "skipFiles": ["<node_internals>/**"], "sourceMaps": true, "outFiles": ["${workspaceFolder}/dist/**/*.js"] }, { "type": "node", "request": "attach", "name": "Attach to REPL Process", "port": 9333, "skipFiles": ["<node_internals>/**"], "sourceMaps": true, "outFiles": ["${workspaceFolder}/dist/**/*.js"] } ], "compounds": [ { "name": "Attach to MCP Server", "configurations": ["Attach to Debug Hook Process", "Attach to REPL Process"] } ] }
Create
.vscode/tasks.json
:{ "version": "2.0.0", "tasks": [ { "type": "npm", "script": "build:watch", "group": { "kind": "build", "isDefault": true }, "problemMatcher": ["$tsc"] } ] }
(Optional) Set breakpoints in your TypeScript files.
Press F5 or use the
Run and Debug
sidebar.
The debugger automatically builds your TypeScript files before launching.