URL Text Fetcher

You set up a tiny MCP server for LM Studio that adds two text-focused tools. It lets you fetch visible page text from a URL and extract all page links, making it easy to build chat prompts, summaries, or link collections from real websites.

How to use

Use the MCP client inside LM Studio to call the two available tools on a target URL. You can fetch the visible text of a page to summarize it, analyze content, or extract key passages. You can also request all links found on a page to build link inventories or perform further crawling.

How to install

Prerequisites you need before starting are installed Python 3.12 or higher and a working internet connection to install dependencies.

Step by step commands to set up and run locally:

cd /Users/lex/Learning/URL-Fetcher-LM-Studio-MCP-Server
python3.12 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip setuptools wheel
python -m pip install -e .

Configuration and local run

You can run the MCP server locally using one of the provided runtime configurations. The server can be started with Python or via the console script if available in your environment.

{
  "mcpServers": {
    "url_text_fetcher": {
      "command": "python",
      "args": ["-m", "url_text_fetcher.mcp_server"],
      "cwd": "/Users/lex/Learning/URL-Fetcher-LM-Studio-MCP-Server"
    }
  }
}

Working prompts (examples)

Use these prompts to interact with the server through LM Studio. Adapt the URLs to your needs.

# Summarize a real page
Use `url_text_fetcher.fetch_url_text` on `https://httpbin.org/html`. Give a two‑sentence summary.

# List links from a real site
Call `url_text_fetcher.fetch_page_links` for `https://www.python.org/` and return the first 10 HTTPS links.

# Answer using content
Fetch text from `https://docs.python.org/3/whatsnew/3.12.html`. What is one notable change in Python 3.12?

Troubleshooting and local run tips

If you encounter ENOENT spawn errors, ensure you run the exact interpreter path shown in your setup. If there are network or SSL issues, try a different URL as some sites block scripted fetches.

To run the local server directly, you can activate the virtual environment and start the server using the Python module command shown above.

Notes

Two tools are exposed by this MCP server: fetch_url_text and fetch_page_links. They are designed to be invoked from within LM Studio via the MCP client, enabling you to fetch text content and extract page links programmatically.

Available tools

fetch_url_text

Fetches visible text from a given URL, returning the readable content without scripts or styling.

fetch_page_links

Fetches and returns all hyperlinks found on a given URL.