Fetch Python

Fetch and transform web content into raw text, rendered HTML, Markdown, or AI-assisted media content using MCP.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 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": {
    "mcp-mirror-tatn_mcp-server-fetch-python": {
      "command": "uv",
      "args": [
        "--directory",
        "path\\\\to\\\\mcp-server-fetch-python",
        "run",
        "mcp-server-fetch-python"
      ],
      "env": {
        "MODEL_NAME": "gpt-4o",
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "PYTHONIOENCODING": "utf-8"
      }
    }
  }
}

You run an MCP server that fetches and transforms web content into raw text, rendered HTML, Markdown, or AI-assisted content from media. This makes it easy to extract structured data, render modern webpages, convert pages to readable Markdown, or analyze images and videos with AI-powered insights when you provide the necessary API key.

How to use

After you have the MCP server available in your client, you can start using its four tools to fetch and transform web content. Use the appropriate tool for your data needs: raw text from URLs, fully rendered HTML for JavaScript-heavy pages, Markdown-formatted output for readable content, or AI-powered extraction from media files. Your MCP client will route requests to the server and display the results in your preferred format.

How to install

Prerequisites: you need a runtime for running MCP servers and a client that can connect to MCP servers. This guide uses a local development setup with the following steps.

# Local installation steps
# Step 1: Clone the project repository (replace with the actual repo URL you are given)
git clone https://github.com/tatn/mcp-server-fetch-python.git

# Step 2: Change to the project directory
cd mcp-server-fetch-python

# Step 3: Prepare and run the MCP server using the MCP control tool
uv sync
uv build

# Step 4: Configure your MCP client to connect to the local server
# The client configuration typically points to the local server runtime as shown in the client setup guide

Additional sections

Configuration and runtime notes: this server provides a dedicated stdio-based MCP connection. You run it locally via a directory-aware command that points the MCP controller to the server’s location. The following configuration snippet shows how to register the server with your MCP client using a local runtime. You should replace the placeholder path with the actual directory where you cloned the server.

{
  "mcpServers": {
    "fetch_python": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "path\\to\\mcp-server-fetch-python",
        "run",
        "mcp-server-fetch-python"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "PYTHONIOENCODING": "utf-8",
        "MODEL_NAME": "gpt-4o"
      }
    }
  }
}

Notes on usage and security

The get-markdown-from-media tool requires an API key in the environment (OPENAI_API_KEY). Ensure you set this key before requesting AI-powered content extraction from media files.

Available tools

get-raw-text

Extracts raw text from a URL without rendering, suitable for structured data formats.

get-rendered-html

Fetches fully rendered HTML using a headless browser to capture JavaScript-generated content.

get-markdown

Converts web page content into clean, well-formatted Markdown while preserving structure.

get-markdown-from-media

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

Built by

VeilStrat

AI signals for GTM teams