An MCP server for fetching and transforming web content into various formats. This server provides comprehensive tools for extracting content from
Fetch Python MCP server exists for a simple reason — assistants are far more useful when they can act on Fetch Python directly instead of describing what you should do. An MCP server for fetching and transforming web content into various formats. This server provides comprehensive tools for extracting content from web pages, including support for JavaScript-rendered content and media files.
Once Fetch Python is connected, these are the calls the assistant has available:
get-raw-text — Extracts raw text content directly from URLs without browser renderingArguments — - url: URL of the target web page (text, JSON, XML, csv, tsv, etc.) (required)get-rendered-html — Fetches fully rendered HTML content using a headless browserget-markdown — Converts web page content to well-formatted Markdownget-markdown-from-media — Performs AI-powered content extraction from media filesTools — The Tools tool exposed by this serverDebugging — You can start the MCP Inspector using npxwith the following commands:You will need 3 environment variables: OPENAI_API_KEY, PYTHONIOENCODING, MODEL_NAME. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at @modelcontextprotocol/inspector on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Fetch Python's toolset — get-raw-text, Arguments, get-rendered-html and 4 more — is a fair guide to whether it matches your workflow. It is maintained by tatn; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| get-raw-text | Extracts raw text content directly from URLs without browser rendering |
| Arguments | - url: URL of the target web page (text, JSON, XML, csv, tsv, etc.) (required) |
| get-rendered-html | Fetches fully rendered HTML content using a headless browser |
| get-markdown | Converts web page content to well-formatted Markdown |
| get-markdown-from-media | Performs AI-powered content extraction from media files |
| Tools | The Tools tool exposed by this server. |
| Debugging | You can start the MCP Inspector using [npx](https://docs.npmjs.com/cli/v11/commands/npx)with the following commands: |
"mcpServers": {
"mcp-server-fetch-python": {
"command": "uvx",
"args": [
"mcp-server-fetch-python"
]
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| PYTHONIOENCODING | Configuration value read at startup. | Optional |
| MODEL_NAME | Configuration value read at startup. | Optional |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.