heroku-agentforce

This repository has 4 different MCP projects that demonstrates some of the inner workings of the MCP and architectural patterns when integrating with various Agents as well as Agentforce.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio mvrzan-heroku-agentforce-mcp node server.js \
  --env PORT="The port the MCP server should listen on. Heroku assigns this automatically." \
  --env MCP_HOST="Optional: host binding if needed." \
  --env MCP_LOG_LEVEL="log level for MCP server (e.g., info, debug)."

How to use

This MCP server hosts the Agentforce integration on Heroku and exposes an MCP server endpoint that the MCP Client can connect to. It enables context provisioning and tool invocation compatible with the MCP standard, specifically supporting the Agentforce workflow and interactions with the surrounding MCP ecosystem. You can point your MCP client at the Heroku app URL to begin exchanging context, prompts, and tool calls with the server, enabling agents to operate using shared capability definitions defined in the MCP configuration. The server is designed to work in tandem with Agentforce’s workflow on Heroku, allowing you to leverage the standardized MCP transports and tool invocation patterns to achieve consistent agent behavior across environments.

How to install

Prerequisites:

Node.js (14.x or newer) and npm
Git
Heroku CLI (optional for deploying to Heroku)

Step-by-step installation:

Clone the repository git clone https://github.com/<username>/mvrzan-heroku-agentforce-mcp.git cd mvrzan-heroku-agentforce-mcp
Install dependencies npm install
Configure environment (local testing). Create a .env file or export vars, for example: PORT=3000 MCP_LOG_LEVEL=info
Run the MCP server locally for testing npm run build (if a build step exists) && node server.js
Deploy to Heroku (optional) heroku create your-app-name git push heroku main heroku config:set PORT=$PORT heroku open

Note: If your project uses a specific start script in package.json, use npm run start accordingly. Ensure any required environment variables described in the mcp_config are set in the hosting environment.

Additional notes

Tips and common issues:

On Heroku, the PORT environment variable is assigned by the platform; ensure the server listens on process.env.PORT.
Verify that the MCP client is configured to connect to the correct Heroku URL and port.
If you see connection issues, check that CORS and network policies allow the MCP client to reach the MCP server endpoint.
Keep dependencies up to date and pin versions to avoid breaking changes in the MCP SDK.
For local testing, you may simulate the Heroku environment by exporting PORT and other env vars before starting the server.
If you modify server behavior, update the MCP configuration accordingly (transport, capabilities, and tools exposed).
Monitor logs (MCP_LOG_LEVEL) to troubleshoot payloads and tool invocations.

Related MCP Servers

gemini-cli

96.1k

An open-source AI agent that brings the power of Gemini directly into your terminal.

ai-trader

491

Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders.

mcp-typescript-sdk

A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.

pluggedin-app

The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.

mcp-discovery

A command-line tool written in Rust for discovering and documenting MCP Server capabilities.

mcpcat-python-sdk

MCPcat is an analytics platform for MCP server owners 🐱.