# AI Support \[Make your documentation easier for AI assistants to read] Vocs includes built-in features that make your documentation easier for LLMs and AI assistants to consume. ## llms.txt Vocs automatically generates [`llms.txt`](https://llmstxt.org/) files for LLM consumption: * `/llms.txt`: A concise index of all pages with titles and descriptions * `/llms-full.txt`: Complete documentation content in a single file These files are generated at build time and served at the root of your site. No configuration required. ### Example Output ```txt # Vocs Vocs is a library for creating documentation websites. - [What is Vocs?](/guide/what-is-vocs): Learn about Vocs and its features - [Getting Started](/guide/getting-started): Quick start guide - [AI Support](/guide/ai-support): Documentation features for AI agents ``` ## Markdown Rendering for AI Agents Vocs automatically detects AI user agents and serves them raw Markdown instead of rendered HTML. This provides better token efficiency and easier parsing for LLMs. ### Supported AI Agents The following user agents are automatically detected: * **OpenAI**: `GPTBot`, `OAI-SearchBot`, `ChatGPT-User` * **Anthropic**: `anthropic-ai`, `ClaudeBot`, `claude-web` * **Google**: `Google-Extended`, `GoogleAgent-Mariner` * **Perplexity**: `PerplexityBot`, `Perplexity-User` * **Mistral**: `MistralAI-User` * **Cohere**: `cohere-ai` * **Others**: `FacebookBot`, `meta-externalagent`, `Bytespider`, `AI2Bot`, and more Search engine crawlers such as `Googlebot`, `Bingbot`, `Amazonbot`, and `Applebot` continue to receive rendered HTML so standard indexing behavior is preserved. ### Manual Markdown Access Most pages can be accessed as Markdown by appending `.md` to the URL: ``` https://docs.example.com/getting-started.md ``` For the home page, use: ``` https://docs.example.com/index.md ``` This is useful for copying documentation into AI conversations or for custom integrations. ## Ask AI Component Vocs includes a built-in "Ask AI" menu (`⌘I` / `Ctrl+I`) that provides: * **Open in ChatGPT/Claude**: Opens the current page context in popular AI assistants * **Copy page for AI**: Copies the page content as Markdown to your clipboard * **View as Markdown**: Opens the raw Markdown version of the current page * **Copy MCP URL**: Copies the MCP server URL (when MCP is enabled) If needed, you can hide the menu for a page with `showAskAi: false` in frontmatter. ## MCP Server Vocs includes a built-in [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that allows AI assistants to navigate your documentation and source code programmatically. Enable it in your Vocs config: ```ts twoslash import { defineConfig } from 'vocs/config' export default defineConfig({ mcp: { enabled: true, }, }) ``` When enabled, the MCP endpoint is available at `/api/mcp`. Most users will want to point their MCP client at a deployed URL such as: ```json { "mcpServers": { "docs": { "url": "https://docs.example.com/api/mcp" } } } ``` The dedicated [MCP Server](/guide/mcp-server) guide covers: * The docs tools Vocs exposes by default * How to connect local and deployed MCP clients * How to expose GitHub repositories and custom source adapters * Security, rate limit, and search behavior considerations ## Best Practices ### Optimize for LLMs 1. **Write descriptive titles**: Use clear, descriptive page titles that help LLMs understand content 2. **Add descriptions**: Include `description` in frontmatter for better llms.txt output 3. **Structure content**: Use headings, lists, and code blocks for easy parsing 4. **Keep pages focused**: Single-topic pages are easier for LLMs to retrieve and reference ### MCP Security * The MCP server only exposes documentation content and configured source repositories * Source code navigation is read-only * Consider using authentication for private documentation * Use `GITHUB_TOKEN` for higher API rate limits when using the GitHub adapter