> For the complete documentation index, see [llms.txt](https://gaffa.dev/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gaffa.dev/docs/ai-tools/gaffa-ai-tools.md).

# 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**](/docs/ai-tools/tools/gaffa-ai-skills.md) - 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](/docs/ai-tools/tools/gaffa-cli.md), which also sets up the MCP server for you.
* [**MCP server**](/docs/ai-tools/tools/gaffa-docs-mcp-server.md) - 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**](https://gaffa.dev/docs/llms-full.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](/docs/ai-tools/tools/gaffa-cli.md) reference for every command and option.

### Where to start

* **Want everything set up in one command?** Use the [Gaffa CLI](/docs/ai-tools/tools/gaffa-cli.md).
* **Building with Gaffa in a coding agent?** Install the [AI skills](/docs/ai-tools/tools/gaffa-ai-skills.md).
* **Want your assistant to look things up in the docs?** Connect the [MCP server](/docs/ai-tools/tools/gaffa-docs-mcp-server.md).
* **Using a chat assistant without MCP?** Use [llms.txt](https://gaffa.dev/docs/llms-full.txt).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://gaffa.dev/docs/ai-tools/gaffa-ai-tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.