Access RedNote Social Media Content

RedNote MCP gives an AI assistant access to Xiaohongshu (RedNote) content - searching notes by keyword and reading note content by URL - authenticated through a persisted browser login session managed via Playwright.

Use it when you want an AI assistant to search Xiaohongshu for notes matching a keyword or read the content of a specific note given its URL. Before first use, you must run the init command to log in through a browser window that opens automatically; once you complete the login manually, the session cookie is saved to ~/.mcp/rednote/cookies.json for reuse. Do not expect comment content retrieval via URL yet - that capability is listed as planned but not yet implemented. Keep the cookie file secure since it contains sensitive session credentials, and refresh it periodically since it can expire.

• Authentication management with persistent cookie storage.
• Keyword search for notes.
• Command-line init tool for interactive login.
• Access note content by URL.

Install Playwright first:

npx playwright install

Then install globally and log in:

npm install -g rednote-mcp
rednote-mcp init

Or build from source:

git clone https://github.com/ifuryst/rednote-mcp.git
cd rednote-mcp
npm install
npm run dev -- init

Configure Cursor:

{
  "mcpServers": {
    "RedNote MCP": {
      "command": "rednote-mcp",
      "args": ["--stdio"]
    }
  }
}

Or via npx: {"command": "npx", "args": ["rednote-mcp", "--stdio"]}. Requires Node.js 16+ and npm 7+. Debug with the MCP Inspector: npx @modelcontextprotocol/inspector npx rednote-mcp --stdio.

Content researchers and marketers who want an AI assistant to search and read Xiaohongshu (RedNote) posts conversationally instead of manually browsing the app.