
Heroku MCP server
Let's your agent access the heroku platform
README
heroku-mcp-server
Overview
The Heroku Platform MCP Server is a specialized Model Context Protocol (MCP) implementation designed to facilitate seamless interaction between Large Language Models and the Heroku Platform. This server aims at providing a robust set of tools and capabilities that enable LLMs to read, manage, and operate Heroku Platform resources.
Key Features:
- Direct interaction with Heroku Platform resources through LLM-driven tools
- Secure and authenticated access to Heroku Platform APIs, leveraging Heroku CLI
- Natural language interface for Heroku Platform interactions
Note: 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.
Installation
Install the Heroku Platform MCP Server globally using npm:
npm -i -g @heroku/mcp-server
Configuration
Authentication Setup
Generate a Heroku authorization token using one of these methods:
- Through your Heroku Dashboard account profile
- Using the Heroku CLI command:
heroku authorizations:create
Copy the token and use it as your HEROKU_API_KEY
in the following steps.
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
"mcpServers": {
"heroku": {
"command": "heroku-mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
Usage with Zed
Add this to your Zed settings.json:
"context_servers": [
"heroku-mcp-server": {
"command": {
"path": "heroku-mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
}
}
],
Usage with Cursor
Add this to your Cursor mcp.json:
"mcpServers": {
"heroku": {
"command": "heroku-mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
},
}
Usage with Windsurf
Add this to your Windsurf mcp_config.json:
"mcpServers": {
"heroku": {
"command": "heroku-mcp-server",
"env": {
"HEROKU_API_KEY": "<YOUR_HEROKU_AUTH_TOKEN>"
}
},
}
Debugging
You can use the MCP inspector or the vscode run/debug to run and debug the server.
- link the project as a global CLI using
npm link
from the project root - build using
npm run build:dev
, or; - to watch for file changes and build automatically use
npm run build:watch
Option 1 - use the @modelcontextprotocol/inspector (no breakpoints in code):
# Breakpoints are not available
npx @modelcontextprotocol/inspector heroku-mcp-server
Option 2 - use the VSCode run/debug launcher (fully functional breakpoints in code):
- Locate and click on the run debug
- select the configuration labeled "MCP Server Launcher" in the dropdown
- click on the green run/debug button
Or if you've installed the package in a specific directory or are developing on it:
cd path/to/servers/src/git
npx @modelcontextprotocol/inspector dist/index.js
VS Code / Cursor Debugging Setup
To setup local debugging with breakpoints:
-
Store your Heroku auth token in VS Code user settings:
- Open Command Palette (Cmd/Ctrl + Shift + P)
- Type "Preferences: Open User Settings (JSON)"
- Add the following:
{ "heroku.mcp.authToken": "your-token-here" }
-
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"] } ] }
-
To debug:
- Set breakpoints in your TypeScript files
- Press F5 or use the Run and Debug sidebar
- The debugger will automatically build your TypeScript files before launching
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.