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

# AI-enhanced documentation

> Leverage intelligent search and LLM-optimized content for faster development

## Smart documentation features

Chift's documentation is optimized for AI consumption, allowing you to get more accurate responses when using our docs as context for LLMs and AI tools.

<CardGroup cols={2}>
  <Card title="AI-Optimized Formats" icon="file">
    Industry-standard formats that help LLMs understand and index our documentation efficiently
  </Card>

  <Card title="Intelligent Search" icon="magnifying-glass">
    Vector-based search through our MCP server for contextual, semantic results
  </Card>
</CardGroup>

## Available AI features

### LLM-optimized files

You can use ready-to-use formats designed for AI tools:

* **[llms.txt](https://docs.chift.eu/llms.txt)** — Industry standard for efficient LLM indexing (like a sitemap for AI)
* **[llms-full.txt](https://docs.chift.eu/llms-full.txt)** — Complete documentation in a single file for AI context
* View page markdown and full text by adding .md at the end of every URL.

### MCP integration

The SearchChift tool is available via our local [MCP server](/ai/mcp#local-installation):

* Search documentation using a vector database approach
* Find results with semantic similarity matching
* Integrate directly with your coding editors

### Chift CLI

The [Chift CLI](/ai/cli) gives coding agents and developers a terminal-first way to explore Chift's API:

* Discover available API operations from the terminal
* Search endpoint metadata with `chift schema search`
* Inspect endpoint input schemas with `--schema`
* Return JSON or YAML output that can be filtered before it is sent back into an AI context

## How to use

<Steps>
  <Step title="Choose your method">
    * **Direct Files** - Use llms.txt or llms-full.txt for AI context
    * **Interactive Search** - Use built-in AI features on documentation pages
    * **MCP Integration** - Connect via SearchChift tool for coding workflows
    * **Chift CLI** - Use terminal-based schema discovery and API calls in coding agents or scripts
  </Step>

  <Step title="Integrate with your tools">
    Connect your preferred AI tools (Claude, ChatGPT, Cursor) to access Chift documentation intelligently.
  </Step>
</Steps>

## SearchChift MCP tool

Our local [MCP server](/ai/mcp#local-installation) includes the `SearchChift` tool that allows your AI to search through our documentation like a vector database. Pass a query and retrieve relevant documentation parts that match semantically.

The SearchChift tool is not available by default and needs to be activated manually by passing the following environment variable.

```
CHIFT_SEARCH=true
```

<CodeGroup>
  ```javascript Node.js theme={null}
  // Search documentation via MCP
  const result = await mcp.call_tool('SearchChift', {
    query: 'How to authenticate webhook requests?'
  });
  ```

  ```python Python theme={null}
  # Use SearchChift tool
  result = await mcp.call_tool('SearchChift', {
      'query': 'Setting up accounting sync'
  })
  ```
</CodeGroup>

<Tip>
  The SearchChift tool helps your coding editor integrate Chift faster by
  providing contextual documentation directly in your development environment.
</Tip>

## Quick access

<CardGroup cols={2}>
  <Card title="Start with MCP" icon="robot" href="/ai/mcp">
    Learn how to set up the MCP server and use SearchChift for documentation
    search
  </Card>

  <Card title="Use the Chift CLI" icon="terminal" href="/ai/cli">
    Explore and call Chift's Unified API from a terminal or coding agent
  </Card>
</CardGroup>