Web Fetcher MCP server
io.github.vojtisprime11/web-fetcher·v0.1.0Turns any web page into clean Markdown, page metadata and classified links for LLMs.
0 stars25 downloads/wk
Reviews
Write oneNobody has reviewed Web Fetcher yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Web Fetcher tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
extract_linksextract_metadatafetch_page_markdown
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan33 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Web Fetcher compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- Tools
- 3
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 25
- more than 11% of 12,191 servers with a package
What its tools let an agent do: 3 read
Install Web Fetcher in Claude Code, Cursor or VS Code
Runs npx -y mcp-server-web-fetcher on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add web-fetcher -- npx -y mcp-server-web-fetcher
What the publisher says
From the Web Fetcher repository's README, as published. We do not edit it. Read it on GitHub
mcp-server-web-fetcher
A fast, dependency-light Model Context Protocol server that turns any web page into something a language model can actually read: clean Markdown, structured metadata, and a classified list of links.
Web pages are 90% chrome. Scripts, cookie banners, navigation, sidebars and tracking pixels burn context and derail reasoning. This server strips all of that on the way in, so the model sees the article and nothing else.
┌────────────┐ stdio/JSON-RPC ┌──────────────────────┐ HTTPS ┌──────────┐
│ MCP client │ ─────────────────► │ mcp-server-web- │ ────────► │ web page │
│ (Claude, │ ◄───────────────── │ fetcher │ ◄──────── │ │
│ Kiro, …) │ Markdown + JSON │ fetch → clean → md │ └──────────┘
└────────────┘ └──────────────────────┘Features
code fences, absolute links. No leftover HTML, even for gnarly nested tables.
- Clean Markdown output. Readability-style main-content detection, GFM tables, language-tagged
being silently cut in half.
- Context-window aware. Long pages are paginated with startIndex / nextStartIndex instead of
Open Graph, Twitter cards, JSON-LD, hreflang alternates, RSS/Atom feeds, h1–h6 outline and raw HTTP headers.
- Structured metadata. Title, description, canonical, lang, author, publish/modify dates,
classification, scope filters, de-duplication.
- Link intelligence. Absolute URLs, anchor text, rel, nofollow, internal vs external
every redirect hop, not just the first request. Credentials in URLs are stripped.
- SSRF hardening. Loopback, private, link-local and cloud-metadata addresses are blocked on
(TIMEOUT, HTTPERROR, BLOCKEDHOST, RESPONSETOOLARGE, …), a retryability flag and a recovery hint, so the model can self-correct instead of guessing.
- Predictable failures. Every error carries a stable machine-readable code
validated structuredContent, not prose they have to re-parse.
- Typed end to end. Strict Zod input schemas plus published outputSchema, so clients get
encodings), a small TTL cache, transient-failure retries and optional robots.txt enforcement.
- Well behaved. Byte caps, timeouts, redirect limits, charset sniffing (including legacy
- 115 tests, no network required. Vitest unit tests plus in-memory MCP protocol tests.
Quickstart
Requires Node.js 20.18.1 or newer (inherited from cheerio, which needs undici 7).
# run it without installing
npx -y mcp-server-web-fetcher
# or install globally
npm install -g mcp-server-web-fetcher
mcp-server-web-fetcherThe server speaks MCP over stdio, so on its own it just waits for a client. Point a client at it:
Claude Desktop
~/Library/Application Support/Claude/claudedesktopconfig.json on macOS, %APPDATA%\Claude\claudedesktopconfig.json on Windows:
{
"mcpServers": {
"web-fetcher": {
"command": "npx",
"args": ["-y", "mcp-server-web-fetcher"]
}
}
}With configuration, using a global install:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Web Fetcher: common questions
- Is Web Fetcher MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Web Fetcher safety report
- How do I install Web Fetcher?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Web Fetcher need an API key?
- No secret keys are declared. It reads 5 settings from the environment.
- Is Web Fetcher maintained?
- The last commit was 41 days ago (2026-09-24). The latest release is v0.1.0.
- What can I use instead of Web Fetcher?
- Servers from other publishers that do the same job: Front-End Checklist MCP server.
- How does Web Fetcher compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Web Fetcher
Same job from other publishers: the closest match first, then the best rated.
- Front-End ChecklistReview frontend code and live pages against 386 quality-gated web development rules.not reviewedWidely usedA