Fetch MCP Server
Retrieve and convert web page content into markdown for AI model processing.
Data last scanned yesterday · Reviewed 2 months ago
Overview
This MCP server enables LLMs to fetch web content and process it directly within the context of their conversation. By retrieving URLs and performing automatic HTML to markdown conversion, it allows agents to read and analyze web data effectively. To manage large pages, the server includes chunking features. Users can specify a start index to extract content in segments, ensuring the model can efficiently parse extensive articles or documentation without exceeding context limits.
Our verdict
With a security score of 76/100, this server is classified as medium risk. Most notably, the README explicitly warns that the server can access local or internal IP addresses, which presents a significant security risk for unauthorized data exposure. It is recommended for users who are comfortable managing network-level access controls and monitoring the URLs fetched by their AI agents.
- Maintained by the official Model Context Protocol organization
- Zero direct dependencies minimize supply-chain surface area
- Robust HTML-to-markdown conversion when Node.js is installed
- Lacks read-only restrictions on URL access
- Directly capable of accessing local and internal network IP addresses
- License is currently set to NOASSERTION
Tools
| Tool | Description | Risk |
|---|---|---|
| fetch | Fetches a URL from the internet and extracts its contents as markdown. | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf | ||||
| ChatGPT |
Frequently asked questions
›Are there any security concerns with using this server?
Yes, the server can access local or internal IP addresses. You should exercise caution to ensure that using this server does not accidentally expose sensitive data.
›How can I handle very long web pages that exceed the character limit?
You can use the start_index argument to specify a character offset. This allows you to fetch content in chunks until you locate the information you need.
›Does this server respect robots.txt files?
Yes, it obeys robots.txt by default when requests are initiated by the model via a tool. You can disable this behavior by adding the --ignore-robots-txt argument to your configuration.
›How can I improve the quality of the HTML to markdown conversion?
Installing Node.js on your system allows the fetch server to utilize a more robust HTML simplifier.
›Can I configure a custom proxy for web requests?
Yes, you can configure the server to use a proxy by adding the --proxy-url argument to your configuration's args list.
›What should I do if I encounter timeout issues on Windows?
You may need to set the PYTHONIOENCODING environment variable to ensure proper character encoding.
Alternatives
Badge
Maintain this server? Add the live badge to your README.