Web Fetcher runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 31 Jul 2026.
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
Nothing serious here today
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.
Connect this server
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": {
"command": "npx",
"args": [
"-y",
"mcp-server-web-fetcher"
]
}
}
}[mcp_servers.web-fetcher]
command = "npx"
args = ["-y", "mcp-server-web-fetcher"]{
"mcpServers": {
"web-fetcher": {
"command": "npx",
"args": [
"-y",
"mcp-server-web-fetcher"
]
}
}
}{
"servers": {
"web-fetcher": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-server-web-fetcher"
]
}
}
}Optional settings from the registry entry, left out of the block above:
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).
Alternatives to Web Fetcher
same job, measured the same wayRead any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Turn any public web page into clean Markdown for LLMs; respects robots.txt. By Crypto Money Maker
Turn any webpage into clean Markdown for LLM/agent pipelines. Free tier; paid 1 USDC = 1000 req.
Turn any web page into clean Markdown for your AI assistant. OAuth sign-in, no API key.
Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).
Web Fetcher — questions
Answers built from our own checks of this server.