Cursor

Cursor connects to the Stableship MCP server and reads AGENTS.md and .cursor/rules from your repository. Once it is connected, ask it in chat to fix what Stableship found; it reads each fix brief, fixes the code and asks Stableship to verify the fix.

Connect

1. Click Add to Cursor, then Install.
2. When Cursor asks you to sign in to Stableship, approve it.

The Add to Cursor button in Stableship's setup and in Settings, then Connections, does step 1 for you, or use this link: Add to Cursor.

Approving opens app.stableship.ai: sign in, pick the workspace and approve. No token to copy. You can disconnect it any time in Stableship: Settings, then Connections, then Connected apps.

Use a token instead

First make a token: in Stableship open Settings, then Connections, open API tokens and connected apps, and choose Create token with Read findings and rules and Start checks and verify fixes. Copy it: it starts with sst_ and is shown once. Use it where these steps say sst_your_token.

Install it with a token:

~/.cursor/mcp.json:

{  "mcpServers": {    "stableship": {      "url": "https://api.stableship.ai/mcp",      "headers": {        "Authorization": "Bearer sst_your_token"      }    }  }}

Keep the token out of your repository.

Check it works

Back in Cursor, Stableship turns green. Start a new chat. Then ask Cursor to list your Stableship projects: it calls list_projects and names your app.

If it does not connect:

• Cursor Settings → MCP: sign in to Stableship from there.
• Or use a token instead.

Keep the rules in your repository

Ask Cursor to call get_repo_files and commit what it returns: .gate/rules.md, .gate/context.md, and a Stableship section in AGENTS.md that tells every chat how to use the rules and the tools. Stableship never writes to your repository, so your agent commits these. If you edit .gate/rules.md and push it, the change comes back to Stableship as a rule suggestion.