browser_install
Install Playwright Chromium browser binary. Call this if you get an error about the browser not being installed.
LABSCO SUMMARY
Pages that need a browser stop being a blind spot.
What it takes off you is the empty response from a client-rendered site: the page is loaded in Chromium, waited on until the state you specify, and only then reduced to text. Passing a list of URLs to one call is the difference between reading a comparison across five sources and reading it five times.
What it is
A Playwright-backed fetcher. Pages are loaded in Chromium, so content that only appears after scripts run is still there when the text is extracted.
What you get
- One URL fetched and returned as extracted content or as raw HTML, capped by length
- Several URLs fetched in one call, with the same options applied to all of them
- Waiting rules you control: a navigation timeout, an overall timeout, and which load state to wait for
- Media loading disabled, for pages where images and video are only weight
- The Chromium binary installed on demand, with or without its system dependencies
Requirements
npx on your PATH. It drives Playwright's Chromium; browser_install fetches that binary when the browser turns out to be missing.
Setup effort
One command — npx -y fetcher-mcp
USE CASES
01
Reading a page that renders after its scripts run
A plain fetch returns an empty shell. Loading in Chromium and waiting for the state you name gets the actual content, with the navigation timeout under your control.
02
Gathering several sources in one pass
Hand over the list of URLs and the same extraction and timeout settings apply to all of them, instead of a call per link.
03
Getting the HTML rather than the reading text
When the markup is the point — checking a tag, an embed or the page structure — turn extraction off and take the raw HTML, capped by length.
04
Getting the browser in place on a fresh machine
The first fetch on a clean install fails because Chromium is not there. One call installs it, with system dependencies if the environment needs them.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
fetch_url
Retrieve web page content from a specified URL
fetch_urls
Retrieve web page content from multiple specified URLs
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 3 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": {
"fetcher-mcp": {
"command": "npx",
"args": [
"-y",
"fetcher-mcp"
]
}
}
}npx
TERMINAL
npx -y fetcher-mcp
