# Heroku MCP connector

Connect Heroku to Elaichi and Claude, ChatGPT, Cursor, or any MCP client can look at and work on the apps, dynos, releases, and add-ons in your Heroku account, with every action logged.

Source: https://elaichi.ai/connectors/heroku/

## Facts

| | |
| --- | --- |
| Application | Heroku |
| Category | Application Development |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Heroku builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | help.heroku.com |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Heroku is connected

- Which apps had a release this week and who deployed them?
- Show the config vars on staging that differ from production.
- List add-ons attached to the billing app and their plans.

## Connect Heroku in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Heroku.
2. Optionally set Share with, then press Connect.
3. Approve it in Heroku. Heroku's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Heroku tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Heroku MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Heroku MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Heroku MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Heroku to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Heroku tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Heroku through Elaichi

### Check what shipped in the last release

Engineering. Ask which release is live on an app, who deployed it, and what changed since the one before, without opening the Heroku dashboard mid-standup.

### Find which app is running short on dynos

Platform. Ask for the dyno sizes and counts across every app in the account, then spot the one that has been running on a single dyno since the last restart.

### Confirm an app is healthy before replying

Support. When a customer reports an outage, ask whether the app's dynos are up and when the last release went out, then answer the ticket with facts rather than guesses.

### See where each app sits in its pipeline

Product. Ask which apps are in staging versus production for a pipeline, and whether the build the team is waiting on has been promoted yet.

### Review who can touch production apps

Security. Pull the collaborators on every production app and compare them with the current team roster before a quarterly access review.

### Tally add-on plans across the account

Finance. List the add-ons attached to each app and the plan each one is on, so the monthly Heroku bill can be matched to the apps that actually use them.

## Elaichi vs Zapier MCP vs Composio for Heroku

All three can connect Heroku to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Heroku tools | Allow or restrict single Heroku tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Heroku call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Heroku to Claude?

Connect Heroku in Elaichi first: pick Heroku from the catalog, a Heroku sign-in window opens, you approve, and the connection is ready. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint.

### Does Heroku work with ChatGPT and Cursor as well as Claude?

Yes. Once Heroku is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Heroku once and every client sees it.

### What can an AI agent actually do with my Heroku account?

It can work on the apps in your Heroku account: list apps and their dynos, read releases and config, check add-ons and pipelines, and make changes where your account allows. Exactly what is available depends on what your Heroku account has set up. Short, concrete asks such as "which apps had a release today" work better than long paragraphs.

### Does connecting Heroku give the AI access to every app in the account?

No. The AI acts as the person who signed in to Heroku, so it sees only the apps and pipelines that person already has access to in Heroku. Elaichi can narrow that further with restrictions, but it can never widen it beyond what Heroku itself grants that person.

### Can my team share one Heroku connection?

Yes. One person connects Heroku in Elaichi and shares the connection with a team, and nobody else handles a Heroku token or password. Each teammate still signs in to Elaichi as themselves, so the audit log names the person behind every Heroku action.

### Can I stop an agent from deleting or changing things in Heroku?

Yes. Restrictions in Elaichi apply per action, so you can allow reading apps, releases, and dynos while blocking anything that deletes an app, changes config, or scales dynos. A restricted action is never advertised to the AI client at all, so no prompt can reach it.

### What happens to a Heroku connection when someone leaves?

Offboarding that person in Elaichi ends their Heroku access through every client at once. A Heroku connection shared with a team keeps working for everyone else. Disconnecting Heroku once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client in the same step.

### Does the Heroku MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Heroku is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Heroku?

Yes. Both let Claude, ChatGPT or Cursor use Heroku. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Heroku call.

### How is Elaichi different from Composio for Heroku?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Heroku: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.