Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Toon Fetch MCP Serverfetch https://news.ycombinator.com and summarize the top story"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Toto Fetch MCP Server
An MCP server that fetches URL content, converts it to Markdown, and optionally processes it with a local LLM (LaMini-Flan-T5). Returns data in TOON format.
Features
Fetch & Clean: Fetches HTML, extracts main content using
@mozilla/readability, and converts to Markdown withturndown.Local AI Processing: Optional local LLM processing using
@huggingface/transformers(runningXenova/LaMini-Flan-T5-248M).TOON Output: Returns structured data in Token-Oriented Object Notation, optimized for agent consumption.
Installation
Build
Usage
As an MCP Server
Add to your MCP client configuration (e.g., Claude Desktop config):
Tool: fetch_url
Arguments:
url(string, required): The URL to fetch.prompt(string, optional): Instruction for the local LLM.Example: "Summarize this article"
Example: "Extract all dates and events"
If omitted, the raw Markdown content is returned.
Output (TOON):
Development
Workflow
Install dependencies:
npm installRun tests:
npm test(uses Vitest)Build:
npx tscVerify: You can use the
src/verify.tsscript (requires build first or ts-node).
Testing
Run unit tests:
License
MIT