fetch
Fetch a webpage and return its content as clean markdown. Auto-detects whether the page requires JavaScript rendering. Use mode="browser" to force Playwright, mode="static" for direct HTTP.
LABSCO SUMMARY
Auto-detection with a manual override is the right default here, because getting it wrong fails silently.
A static fetch of a JavaScript-rendered page returns a shell rather than an error, which is the failure that wastes the most time; fetch and fetch_raw both detect the need for rendering and both take mode, so either path can be forced when the detection guesses wrong. maxLength on the markdown fetch is what keeps a long page out of the whole context window, and the screenshot's 2MB ceiling is stated up front rather than found on a tall page.
What it is
A page fetcher with three tools — markdown extraction, raw HTML and a screenshot — each auto-detecting whether the page needs JavaScript rendering and each accepting an explicit mode.
What you get
- fetch returns a page as clean markdown, auto-detecting whether JavaScript rendering is required, with mode="browser" forcing Playwright and mode="static" forcing direct HTTP, and maxLength bounding the output.
- fetch_raw returns the raw HTML, for when the structure rather than the extracted text is what you need.
- screenshot returns a base64-encoded PNG, with fullPage for the whole document; output is limited to 2MB.
Requirements
Nothing — no account, no key. The browser path runs Playwright on the host, and screenshot output is capped at 2MB.
Setup effort
One command — npx -y render-fetch
USE CASES
01
Reading a page as text without the markup around it
Rendering is detected automatically and the output length is bounded, so a long page does not arrive whole.
02
Getting the HTML structure rather than the text
Raw HTML is the right output when the question is about attributes, structure or embedded data rather than prose.
03
Confirming visually what a page actually shows
A screenshot settles what text extraction cannot, and the full-page option covers content below the fold within a 2MB limit.
04
Forcing a browser render when the detection guessed wrong
A static fetch of a JavaScript page returns a shell rather than an error, and the mode parameter is how you rule that out.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
fetch_raw
Fetch a webpage and return its raw HTML. Auto-detects whether JavaScript rendering is needed. Useful when you need the HTML structure rather than extracted text.
screenshot
Take a screenshot of a webpage. Returns a base64-encoded PNG. Useful for visual verification of page content. Limited to 2MB output.
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": {
"render-fetch": {
"command": "npx",
"args": [
"-y",
"render-fetch"
]
}
}
}npx
TERMINAL
npx -y render-fetch
