Turns any web page into clean Markdown, page metadata and classified links for LLMs.
Connect Runs on your machine
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 [email protected]{
"mcpServers": {
"web-fetcher": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"WEB_FETCHER_TIMEOUT_MS": "<WEB_FETCHER_TIMEOUT_MS>",
"WEB_FETCHER_MAX_BYTES": "<WEB_FETCHER_MAX_BYTES>",
"WEB_FETCHER_USER_AGENT": "<WEB_FETCHER_USER_AGENT>",
"WEB_FETCHER_ALLOW_PRIVATE_HOSTS": "<WEB_FETCHER_ALLOW_PRIVATE_HOSTS>",
"WEB_FETCHER_RESPECT_ROBOTS": "<WEB_FETCHER_RESPECT_ROBOTS>"
}
}
}
}{
"mcpServers": {
"web-fetcher": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"WEB_FETCHER_TIMEOUT_MS": "<WEB_FETCHER_TIMEOUT_MS>",
"WEB_FETCHER_MAX_BYTES": "<WEB_FETCHER_MAX_BYTES>",
"WEB_FETCHER_USER_AGENT": "<WEB_FETCHER_USER_AGENT>",
"WEB_FETCHER_ALLOW_PRIVATE_HOSTS": "<WEB_FETCHER_ALLOW_PRIVATE_HOSTS>",
"WEB_FETCHER_RESPECT_ROBOTS": "<WEB_FETCHER_RESPECT_ROBOTS>"
}
}
}
}{
"servers": {
"web-fetcher": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"WEB_FETCHER_TIMEOUT_MS": "<WEB_FETCHER_TIMEOUT_MS>",
"WEB_FETCHER_MAX_BYTES": "<WEB_FETCHER_MAX_BYTES>",
"WEB_FETCHER_USER_AGENT": "<WEB_FETCHER_USER_AGENT>",
"WEB_FETCHER_ALLOW_PRIVATE_HOSTS": "<WEB_FETCHER_ALLOW_PRIVATE_HOSTS>",
"WEB_FETCHER_RESPECT_ROBOTS": "<WEB_FETCHER_RESPECT_ROBOTS>"
}
}
}
}Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
WEB_FETCHER_TIMEOUT_MSOptional | Request timeout in milliseconds (1000-120000). Defaults to 15000. |
WEB_FETCHER_MAX_BYTESOptional | Maximum bytes downloaded per response. Defaults to 5000000. |
WEB_FETCHER_USER_AGENTOptional | User-Agent header sent with every request. |
WEB_FETCHER_ALLOW_PRIVATE_HOSTSOptional | Set to true to allow fetching loopback and private network addresses. Disables the SSRF guard. |
WEB_FETCHER_RESPECT_ROBOTSOptional | Set to true to enforce robots.txt before fetching. |
Details
| Package | [email protected] (NPM, stdio) |
| First published | 30 Jul 2026 |
| Last updated | 30 Jul 2026 |
| Registry name | io.github.vojtisprime11/web-fetcher |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.