fetch_html
Fetch a website and return its unmodified contents as HTML
LABSCO SUMMARY
It stops a model spending its context on navigation bars.
The six tools are really one decision made per call: how much of the page the model should see. fetch_readable on an article costs a fraction of fetch_html on the same URL, and fetch_json skips the parsing step altogether. Because headers and a proxy are parameters on every tool, the pages that need a session cookie or a particular egress route stay reachable.
What it is
A local server with six fetch tools that differ in what they hand back: HTML, Markdown, plain text, JSON, Readability-parsed article text, or captions from a YouTube page. Every one takes custom headers, a proxy, and start_index / max_length for paging.
What you get
- Fetch a page as unmodified HTML (fetch_html) or converted to Markdown (fetch_markdown).
- Strip the tags entirely for plain text (fetch_txt), or read a JSON endpoint directly (fetch_json).
- Get the article and nothing else — fetch_readable runs Mozilla Readability to drop navigation, ads and boilerplate before converting to Markdown.
- Pull captions from a YouTube video page in a chosen language (fetch_youtube_transcript).
- Send your own headers, route through a proxy, and page long responses with start_index and max_length on every tool.
Requirements
Node.js on the machine, and nothing else — no account, no key. MIT licensed.
Setup effort
One command — npx mcp-fetch-server
USE CASES
01
Reading an article the model cannot otherwise open
Get the body text without the site furniture, in a form that quotes cleanly.
02
Pulling data out of a JSON endpoint
Read the API response directly rather than scraping a rendered page.
03
Working through a page too long for one response
Page the document with an offset and a length cap instead of truncating it blindly.
04
Getting the content of a video without watching it
Take the captions off the video page and work from those.
05
Checking what a page actually serves
Look at the markup as delivered, headers and all, when the rendered text is not the question.
6 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
fetch_json
Fetch a JSON file from a URL
fetch_markdown
Fetch a website and return its contents converted to Markdown
fetch_readable
Fetch 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_txt
Fetch a website, convert the content to plain text (no HTML)
fetch_youtube_transcript
Fetch a YouTube video page and extract its captions/transcript
BEFORE YOU INSTALL
What to know first
Tools you get
6 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 6 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mcp-fetch-server": {
"command": "npx",
"args": [
"mcp-fetch-server"
]
}
}
}npx
TERMINAL
npx mcp-fetch-server
