Connect your agent (MCP)
Helicarrier speaks MCP (Model Context Protocol), so you can drive your whole account from an AI agent — Claude, Cursor, or anything that speaks MCP. Ask it to deploy a service, tail logs, set an environment variable, roll back a bad deploy, or provision a database, and it calls Helicarrier for you.
1. Create an API key
Section titled “1. Create an API key”An agent authenticates with a personal API key. In Settings → Your account → API keys:
- Give the key a name (e.g. Claude agent).
- Optionally check Read-only — the key can view everything but can’t change anything (safe for an agent that only inspects). Leave it unchecked for full control.
- Click Create key and copy it immediately — it’s shown only once (it starts with
heli_).
A key acts as you — the same access you have in the dashboard, nothing more (it can’t touch operator settings). Revoke it any time from the same screen; anything using it stops instantly.
2. Point your MCP client at the endpoint
Section titled “2. Point your MCP client at the endpoint”The endpoint is shown on the same page:
https://app.helicarrier.xyz/mcpConfigure your MCP client with that URL and an Authorization: Bearer header carrying your key. For a client that uses a JSON config, it looks like:
{ "mcpServers": { "helicarrier": { "url": "https://app.helicarrier.xyz/mcp", "headers": { "Authorization": "Bearer heli_your_key_here" } } }}(Exact config varies by client — use its “remote/HTTP MCP server” option and set the URL + Authorization header.)
3. Ask your agent
Section titled “3. Ask your agent”Once connected, your agent can:
- See things — list projects and services, read a service’s status, deployments, logs, env keys, and domains.
- Ship things — create a service (from a Git repo, an image, or an uploaded folder with
deploy_upload), deploy, roll back, scale, stop, or delete it. - Configure things — set environment variables, add a custom domain, provision a managed database.
The deploy_upload tool lets an agent deploy local code with no git repo: pipe your project folder as a base64-encoded .tar.gz. Keep it to source (exclude node_modules/.git); very large contexts should use the dashboard upload flow.
Destructive actions (deploy, rollback, delete, scale, env changes, and the like) are flagged, so a well-behaved client will confirm with you before running them. If you created a read-only key, those tools aren’t offered at all.
Your projects are also exposed as MCP resources, so a client that supports resources can attach a project (its services, environments, and config) as context for the conversation.