io.github.vojtisprime11/web-fetcherweb-automation

web-fetcher

Verified · 21 days ago

Turns any web page into clean Markdown, page metadata and classified links for LLMs.

Install

claude mcp add web-fetcher -- npx -y [email protected]

Requires: WEB_FETCHER_TIMEOUT_MS, WEB_FETCHER_MAX_BYTES, WEB_FETCHER_USER_AGENT, WEB_FETCHER_ALLOW_PRIVATE_HOSTS, WEB_FETCHER_RESPECT_ROBOTS

Our take

Converts web pages into cleaner Markdown plus metadata and link classifications, which is a practical preprocessing step for LLM and retrieval workflows. It is well suited to developers building browse, scrape, or summarize features that need less noisy page content. The function is straightforward and useful, though the metadata here still suggests an early or lightly maintained project rather than an established standard.

reviewed by hand · 2026-07-31

Something wrong or dead here? Report it

Verification record

last verified
21 days ago
github stars
0
last commit
31 days ago
archived
no
license
MIT
npm
mcp-server-web-fetcher
latest version
0.1.0
in registry since
2026-07-30

github.com/vojtisprime11/mcp-server-web-fetcher

More in web-automation

browse all →
browser-useweb-automation

browser-use

Verified · 13 days ago

Control a real Chrome browser to complete any task: fill forms, extract data, book flights.

hand-reviewed112k starschecked 13 days ago

Scraplingweb-automation

Scrapling MCP Server

Verified · 6 days ago

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

hand-reviewed79k starschecked 6 days ago

aihawkweb-automation

AIHawk

Verified · yesterday

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

hand-reviewed30k starschecked yesterday

skyvernweb-automation

Skyvern

Verified · 3 days ago

AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

hand-reviewed23k starschecked 3 days ago