Fetch MCP provides tools for retrieving and converting web content into multiple formats including HTML, plain text, Markdown, JSON, and readable article extracts. The server offers six primary tools—fetch_html, fetch_txt, fetch_markdown, fetch_json, fetch_readable (using Mozilla Readability), and fetch_youtube_transcript—each accepting common parameters like custom headers, character limits, start indices, and proxy configuration. It solves the problem of extracting and reformatting web content for AI applications by handling format conversion, content cleanup, and transcript retrieval across diverse source types.
claude mcp add --transport stdio zcaceres-fetch-mcp uvx fetch-mcp