Use the docs with AI agents

Give Cursor, Claude, VS Code, Windsurf or any AI agent the FeatherPanel docs. Connect the docs MCP server, or read llms.txt, llms-full.txt and per-page Markdown.

The documentation is available to AI tools in three ways:

MCP server

The docs MCP server uses the Streamable HTTP transport at https://featherpanel.com/mcp. It is read-only and needs no authentication. It has three tools:

product is one of panel, wings, quilld, cli or api.

Cursor

Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:

{
  "mcpServers": {
    "featherpanel-docs": {
      "url": "https://featherpanel.com/mcp"
    }
  }
}

Claude Code

claude mcp add --transport http featherpanel-docs https://featherpanel.com/mcp

Claude Desktop

In Claude Desktop, open Settings, then Connectors, choose “Add custom connector” and enter https://featherpanel.com/mcp. On versions without custom connectors, bridge the remote server through mcp-remote in claude_desktop_config.json:

{
  "mcpServers": {
    "featherpanel-docs": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://featherpanel.com/mcp"]
    }
  }
}

VS Code

Add this to .vscode/mcp.json in your workspace, or run “MCP: Add Server” from the command palette:

{
  "servers": {
    "featherpanel-docs": {
      "type": "http",
      "url": "https://featherpanel.com/mcp"
    }
  }
}

Windsurf

Add this to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "featherpanel-docs": {
      "serverUrl": "https://featherpanel.com/mcp"
    }
  }
}

Test it with curl

curl -s https://featherpanel.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_docs","arguments":{"query":"install wings"}}}'

llms.txt

/llms.txt lists every docs page with a one-line description and a link to its Markdown version, grouped by product. /llms-full.txt contains every page in one file. It is large because it includes the full API reference, so prefer llms.txt or the MCP server when your tool has a small context window.

Markdown pages

Every docs page is also published as Markdown at the same address with .md added:

The “Copy as Markdown” and “View .md” buttons at the top of each page do the same thing from the browser. Each Markdown page has a <link rel="alternate" type="text/markdown"> tag in its HTML, so crawlers can find it.

Crawling

/robots.txt allows AI crawlers such as GPTBot, ClaudeBot, PerplexityBot and Google-Extended, and points to the sitemap, which lists every docs page.