Web Fetcher runs on your own machine — the client starts it, so there is no endpoint to ping. 33 installs a week from npm. Last commit 31 Jul 2026.
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
Today is the operative word: we check Web Fetcher every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add web-fetcher -- npx -y mcp-server-web-fetcher
{
"mcpServers": {
"web-fetcher": {
"args": [
"-y",
"mcp-server-web-fetcher"
],
"command": "npx"
}
}
}
[mcp_servers.web-fetcher]
command = "npx"
args = ["-y", "mcp-server-web-fetcher"]
{
"mcpServers": {
"web-fetcher": {
"args": [
"-y",
"mcp-server-web-fetcher"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"web-fetcher": {
"args": [
"-y",
"mcp-server-web-fetcher"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
WEB_FETCHER_TIMEOUT_MS (Request timeout in milliseconds (1000-120000). Defaults to 15000.), WEB_FETCHER_MAX_BYTES (Maximum bytes downloaded per response. Defaults to 5000000.), WEB_FETCHER_USER_AGENT (User-Agent header sent with every request.), WEB_FETCHER_ALLOW_PRIVATE_HOSTS (Set to true to allow fetching loopback and private network addresses. Disables the SSRF guard.), WEB_FETCHER_RESPECT_ROBOTS (Set to true to enforce robots.txt before fetching.).
The author declared them in the registry entry; get the values from the project itself.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
URL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.
Paid fallback for public webpages: clean text, Markdown, links, metadata, and JavaScript rendering.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Turn HTML or Markdown into a clean, styled PDF and get a download link.
Cloud scraping & crawling API for AI agents. Turn any URL into clean, LLM-ready markdown.
Live web search and clean-markdown page fetch over the Keenable web index.
Answers built from our own checks of this server.