Atlas / MCP servers / zcaceres / mcp-fetch-server

mcp-fetch-serverSAFE

mcp/zcaceres/fetch-mcp

A flexible HTTP fetching Model Context Protocol server.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
6 6r · 0w · 0d
Transport
stdio
License
MIT
Stars
826
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/mcp-fetch-server)

An MCP server for fetching web content in multiple formats — HTML, JSON, plain text, Markdown, readable article content, and YouTube transcripts.

Tools

All tools accept the following common parameters:

  • fetch_html — Fetch a website and return its raw HTML content.
  • fetch_markdown — Fetch a website and return its content converted to Markdown.
  • fetch_txt — Fetch a website and return plain text with HTML tags, scripts, and styles removed.
  • fetch_json — Fetch a URL and return the JSON response.
  • fetch_readable — Fetch a website and extract the main article content using Mozilla Readability, returned as Markdown. Strips navigation, ads, and boilerplate. Ideal for articles and blog posts.
  • fetch_youtube_transcript — Fetch a YouTube video's captions/transcript. Uses yt-dlp if available, otherwise extracts directly from the page. Accepts an additional lang parameter (default: "en") to select the caption language.

Installation

As an MCP server

Add to your MCP client configuration:

{
"mcpServers": {
"fetch": {
"command": "npx",
"args": ["mcp-fetch-server"]
}
}
}

As a CLI

npx m
Read from source at commit 3f4361d01094OBSERVED · 2026-10-12
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add mcp-fetch-server -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-fetch-server": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (6)

6 read · 0 write · 0 destructive.

ToolRiskDescription
fetch_htmlreadFetch a website and return its unmodified contents as HTML
fetch_jsonreadFetch a JSON file from a URL
fetch_markdownreadFetch a website and return its contents converted to Markdown
fetch_readablereadFetch a website and return its main content parsed by Mozilla Readability, converted to Markdown. Strips away navigation, ads, and boilerplate. Ideal for articles and blog posts.
fetch_txtreadFetch a website, convert the content to plain text (no HTML)
fetch_youtube_transcriptreadFetch a YouTube video page and extract its captions/transcript
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (1 observation(s))
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
src/Fetcher.test.ts:211
url: "http://127.0.0.1/internal",
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @mozilla/readability, jsdom, private-ip, turndown, zod, @types/bun, @types/jsdom
Why it matters. 10 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
logo.jpg
logo.jpg
Why it matters. 1026835 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 3f4361d01094full audit observations/trust-audit/mcp-server/zcaceres__fetch-mcp.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-123f4361d01094SAFEB89first audit
06

Questions

What is the mcp-fetch-server MCP server?

A flexible HTTP fetching Model Context Protocol server.

What tools does mcp-fetch-server expose?

6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is mcp-fetch-server safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does mcp-fetch-server need?

No credential environment variables were found in its source, so it appears to need none.

How does mcp-fetch-server run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-fetch-server at 1.1.2.

How current is this page?

The grade is for one exact copy of the source (3f4361d01094), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement