> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rafftechnologies.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Raff docs in your AI tools

> Connect the read-only Raff documentation MCP server so your AI assistant answers Raff questions from the current docs. No sign-in needed.

<sub>Updated October 11, 2026</sub>

Raff's documentation has its own MCP server at `https://docs.rafftechnologies.com/mcp`. It is public and read-only: no sign-in, no account, and it cannot see or change anything in Raff. Connect it when you only want accurate answers about Raff, for example in a tool where you do not want account access.

The [Raff MCP server](/products/ai/mcp) already includes documentation search (`search_docs`), so you do not need both.

## What it gives the assistant

| Tool | What it returns |
| - | - |
| **Search** | Matching passages from every published Raff docs page, with links |
| **Read a page** | A specific page by its docs path, for example `products/build/virtual-machines/quickstart-guides/create-a-vm` |

## Connect

<Tabs>
  <Tab title="Claude">
    **Customize → Connectors → + Add → Add custom connector**, name `Raff docs`, URL `https://docs.rafftechnologies.com/mcp`, and choose no sign-in.
  </Tab>

  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add --transport http raff-docs https://docs.rafftechnologies.com/mcp
    ```
  </Tab>

  <Tab title="Cursor">
    In `~/.cursor/mcp.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "raff-docs": { "url": "https://docs.rafftechnologies.com/mcp" }
      }
    }
    ```
  </Tab>

  <Tab title="Other apps">
    Add a remote MCP server with the URL `https://docs.rafftechnologies.com/mcp` and no authentication.
  </Tab>
</Tabs>

## Example questions

* *"Show me the curl call to create a Raff VM in a specific project."*
* *"How do I move a reserved IP between two Raff VMs?"*
* *"Write a Terraform module for a Raff VM with a 100 GB volume."*

The assistant searches the docs and answers with Raff's real endpoints, field names and dashboard paths, with links to the pages it used.

## Next steps

<CardGroup cols={2}>
  <Card title="Raff MCP server" icon="robot" href="/products/ai/mcp">
    Let the assistant work in your account, not only read the docs.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/endpoints">
    Every endpoint the docs describe.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.