get-raw-textLABSCO SUMMARY
Four fetches, because pages do not all behave the same.
A single-page app returns nothing useful to a plain fetch, and a JSON endpoint has no need of a browser. Keeping the raw, rendered, Markdown and media paths as separate tools means the right one is chosen per URL instead of fighting one general fetcher.
What it is
A fetching server with four ways to bring a URL back: raw text with no browser, fully rendered HTML from a headless browser for JavaScript-driven pages, well-formatted Markdown, and AI-powered extraction from images and video.
What you get
- Raw text pulled straight from a URL, for JSON, XML, CSV, TSV and other structured formats (get-raw-text)
- Fully rendered HTML from a headless browser, for modern apps and SPAs that need JavaScript to run (get-rendered-html)
- A page converted to clean Markdown with its structure preserved (get-markdown)
- Content extracted from images and video using computer vision and OCR (get-markdown-from-media)
- The right fetch chosen per URL, rather than one general fetcher used for everything
Requirements
uvx, which runs it with nothing installed. The media tool needs an OpenAI key and returns an error without one; the model it uses defaults to gpt-4o and can be overridden, and PYTHONIOENCODING can be set to utf-8 if output encoding misbehaves.
Setup effort
One command — uvx mcp-server-fetch-python
USE CASES
01
Reading a page that comes back empty
The headless browser renders the JavaScript first, which is what makes an SPA or a modern web app readable at all.
02
Getting an article into a readable form
The page converts to Markdown with headings and structure intact, so the assistant reads prose rather than markup.
03
Pulling a structured feed
JSON, XML, CSV and TSV come back as raw text with no browser in the way, which is faster and does not mangle the format.
04
Reading text that only exists inside an image
Computer vision and OCR extract the content of an image or video at a URL, for the chart or screenshot that carries the actual number.
4 tools
Listed in project docs. Your client may show a different list.
get-rendered-htmlget-markdownget-markdown-from-mediaBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
uvx on PATH
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-server-fetch-pythonMCP Clients
Claude Desktop — uvx
CLAUDE DESKTOP — UVX · JSON
{
"mcpServers": {
"mcp-server-fetch-python": {
"command": "uvx",
"args": [
"mcp-server-fetch-python"
]
}
}
}Claude Desktop — local build
CLAUDE DESKTOP — LOCAL BUILD · JSON
{
"mcpServers": {
"mcp-server-fetch-python": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_SERVER_FETCH_PYTHON>",
"run",
"mcp-server-fetch-python"
]
}
}
}
