export declare const platformMcpMdxTemplate = "---\ntitle: \"MCP\"\ndescription: \"Connect external AI apps like Claude and Cursor to your documentation with a Model Context Protocol server, and protect it with an API key.\"\ndate: \"2026-07-12\"\nupdated: \"2026-07-30\"\ncategory: \"AI & Integrations\"\ncategoryOrder: 3\norder: 1\nsection: \"Platform\"\n---\n# MCP\n\nThe **MCP** settings page lets external AI applications connect to your documentation through a hosted Model Context Protocol (MCP) server. Every Doccupine site exposes an MCP endpoint at `/api/mcp` that AI tools can query to search and read your content.\n\n## Connect your site with AI apps\n\nThe **Connect your site with AI apps** card gives you a ready-to-paste MCP configuration for popular AI tools. Pick a tab, copy the snippet, and add it to that tool's MCP config:\n\n- **Claude** - add the configuration to Claude Desktop's `claude_desktop_config.json`, or add the server URL as a connector from Claude's settings.\n- **Cursor** - add the configuration to Cursor's `~/.cursor/mcp.json`, or connect it from Cursor's MCP settings.\n- **Others** - a generic `mcpServers` block for any MCP-compatible application.\n\nEvery snippet points to your site's own MCP endpoint, for example:\n\n```json\n{\n  \"mcpServers\": {\n    \"Your Project\": { \"url\": \"https://your-site.com/api/mcp\" }\n  }\n}\n```\n\n<Callout type=\"note\">\n  The connection snippet appears once your site has been deployed. If you haven't published yet, deploy your site first to get its MCP server URL.\n</Callout>\n\n## MCP server authentication\n\nOn a public site, the MCP endpoint is publicly accessible by default. When the site is [password protected](/platform/authentication), MCP requires the same session unless you configure its dedicated API key:\n\n1. Enable **Require API key for MCP access**.\n2. Enter an API key.\n3. Save.\n\nOnce enabled, clients must include the key as a Bearer token in the `Authorization` header of every request to `/api/mcp`.\n\n<Callout type=\"warning\">\n  The API key is stored as an environment variable (`DOCS_API_KEY`) on your deployment, not in a JSON file. After saving, a redeploy is triggered automatically to apply the change.\n</Callout>\n\n<Callout type=\"note\">\n  For the full reference on how the MCP server works - available tools, rate limits, and endpoint details - see the [Model Context Protocol documentation](/model-context-protocol).\n</Callout>";