Fetch Python

Fetches and transforms web content from URLs into raw text, rendered HTML, Markdown, or AI-assisted media content.

python

7

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "tatn-mcp-server-fetch-python": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch-python"
      ],
      "env": {
        "MODEL_NAME": "gpt-4o",
        "OPENAI_API_KEY": "YOUR_API_KEY_PLACEHOLDER",
        "PYTHONIOENCODING": "utf-8"
      }
    }
  }
}

You have a versatile MCP server that fetches and converts web content into raw text, rendered HTML, Markdown, or AI-powered media-derived data. It helps you integrate web content into your workflows with flexible rendering and output formats, including support for modern JavaScript-rendered pages and media analysis.

How to use

You connect your MCP client to this server via an MCP configuration. Choose the tool that matches your goal and call it through the MCP interface. For quick usage, select one of the built-in tools to extract or transform page content from a URL. If you need AI-powered analysis of media, provide a media URL and ensure you have an API key set.

How to install

Prerequisites: you need a runtime environment that can run MCP servers and a client capable of loading MCP configurations.

Create a local MCP server configuration using the provided command to run the server locally via the MCP runner.
Add a configuration entry for the server in your MCP client configuration so your client can reach the server.
If you want to run the server locally from source, follow the steps shown below to clone the repository, synchronize with the MCP runtime, and start the server.

Additional notes

This server exposes four tools for content extraction and transformation. The media-based Markdown tool requires an OPENAI_API_KEY to be set in your environment. If character encoding issues arise, you can set PYTHONIOENCODING to utf-8 and optionally specify a preferred MODEL_NAME for the AI model.

If you are wiring this into Claude Desktop, you can add the MCP server entry using the provided configuration snippet to enable seamless startup from your desktop client.

Configuration and troubleshooting

Configuration is expressed as a standard MCP server entry. The server operates in stdio mode, which means you launch a local process that communicates with the MCP runtime. Ensure you provide any required environment variables, particularly OPENAI_API_KEY for media-based content extraction.

If you encounter encoding issues, set PYTHONIOENCODING to utf-8 in the server environment. If you want to influence AI model selection, you can set MODEL_NAME to your preferred model.

Available tools

get-raw-text

Extracts raw text content directly from URLs without browser rendering. Use this for structured data formats where fast, direct access is needed.

get-rendered-html

Fetches fully rendered HTML content using a headless browser. Essential for modern web apps and SPAs that rely on JavaScript rendering.

get-markdown

Converts web page content to well-formatted Markdown, preserving structure while delivering clean, readable text.

get-markdown-from-media

Performs AI-powered content extraction from media files (images, videos) using computer vision and OCR. Requires a valid OPENAI_API_KEY.