web fetcher MCP
v0.1.0io.github.vojtisprime11/web-fetcher
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
transport:stdio
runtime:npm
Target client
run in your project directory
claude mcp add web-fetcher -e WEB_FETCHER_TIMEOUT_MS=<WEB_FETCHER_TIMEOUT_MS> -e WEB_FETCHER_MAX_BYTES=<WEB_FETCHER_MAX_BYTES> -e WEB_FETCHER_USER_AGENT=<WEB_FETCHER_USER_AGENT> -e WEB_FETCHER_ALLOW_PRIVATE_HOSTS=<WEB_FETCHER_ALLOW_PRIVATE_HOSTS> -e WEB_FETCHER_RESPECT_ROBOTS=<WEB_FETCHER_RESPECT_ROBOTS> -- npx -y mcp-server-web-fetcher
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.