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

# Building with AI

> Use AI coding assistants to build with peaq faster

peaq documentation is built for AI coding assistants. Claude, Cursor, GitHub
Copilot and other tools can read it directly for details on the peaq SDKs and
APIs.

## Machine-readable docs

### llms.txt files

peaq docs follow the [llms.txt standard](https://llmstxt.org/):

| File | URL | Description |
| - | - | - |
| **llms.txt** | `https://docs.peaq.xyz/llms.txt` | Navigation structure with page summaries |
| **llms-full.txt** | `https://docs.peaq.xyz/llms-full.txt` | Complete documentation in plain text |

Both files are generated from the live documentation.

### Copy a single page

Click **Copy page** at the top of any docs page to copy its contents in a clean,
AI-friendly format, then paste that into your assistant's context window.

## Cursor

### MCP server

The peaq docs MCP server gives Cursor, Claude Desktop, or any MCP client
queryable access to the documentation. Add it to Cursor in `.cursor/mcp.json`
(per project) or `~/.cursor/mcp.json` (global):

```json theme={"theme":{"light":"github-light-default","dark":"github-dark"}}
{
  "mcpServers": {
    "peaq-docs": {
      "url": "https://docs.peaq.xyz/mcp"
    }
  }
}
```

### Cursor @Docs

Add peaq docs as a context source in Cursor:

1. Open Cursor Settings → Features → Docs
2. Add `https://docs.peaq.xyz` as a documentation source
3. Reference it in any Cursor chat by typing `@Docs` and selecting peaq

## Claude

### Claude Projects

Create a dedicated Claude Project for peaq development:

1. Create a new project in [Claude](https://claude.ai)
2. Add `https://docs.peaq.xyz/llms-full.txt` as a knowledge source
3. Set custom instructions like *"Use the peaq documentation to answer questions
   about the peaq SDK and APIs"*

### Claude Code

Add the following to your `.mcp.json` for context-aware assistance in your terminal:

```json theme={"theme":{"light":"github-light-default","dark":"github-dark"}}
{
  "mcpServers": {
    "peaq-docs": {
      "type": "http",
      "url": "https://docs.peaq.xyz/mcp"
    }
  }
}
```

Or add it from the command line:

```bash theme={"theme":{"light":"github-light-default","dark":"github-dark"}}
claude mcp add --transport http peaq-docs https://docs.peaq.xyz/mcp
```

## Prompting tips

When prompting any AI assistant about peaq:

* **Name the SDK**: say whether you are using the JavaScript SDK, the Python SDK,
  or calling the API directly, so the model generates the right patterns.
* **Name the function**: say which part of the SDK you need (DID operations, RBAC
  operations, storage operations, data verification tiers, or UMT), or which
  peaqOS function (for example activate or peaqOS Verify).
* **Name the network**: say whether you target peaq mainnet or agung testnet, so
  you get the right endpoints and config values.
* **Paste the page**: use **Copy page** on the docs page you are working from.


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