For the complete documentation index, see llms.txt. This page is also available as Markdown.

Gaffa AI Tools

Use Gaffa with your favourite AI coding tools.

AI assistants write much better code when they have accurate, up-to-date context about the API they're using. Gaffa gives your AI tools that context, so you can ask for working Gaffa code without pasting documentation into every chat.

What's available

There are three ways to connect Gaffa to your AI tools:

  • AI skills - teach your coding agent to write and review Gaffa code, find information on a live website, debug a failing request, and prepare a support report. They work in Claude Code, Codex, Cursor, GitHub Copilot, Antigravity, and Pi. Install them with one command using the Gaffa CLI, which also sets up the MCP server for you.

  • MCP server - gives any tool that supports MCP live access to the Gaffa docs. Your assistant searches and reads only the pages it needs, and always gets the latest version. It needs no API key, and it can't access your account or spend credits.

  • llms.txt - a single file with a concise overview of the Gaffa API that you can paste into any AI assistant, such as ChatGPT or Claude. It's a snapshot of the docs, so use it when your tool doesn't support MCP.

To set up the skills and the MCP server in one step, run npx @gaffa-dev/cli install. See the Gaffa CLI reference for every command and option.

Where to start

  • Want everything set up in one command? Use the Gaffa CLI.

  • Building with Gaffa in a coding agent? Install the AI skills.

  • Want your assistant to look things up in the docs? Connect the MCP server.

  • Using a chat assistant without MCP? Use llms.txt.

Last updated