Fetch
Fetch is hosted online, so all tools can be tested directly either in theTools tabor in theOnline Client.
If you are the rightful owner of Fetch and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.
A Model Context Protocol server that provides web content fetching capabilities, enabling LLMs to retrieve and process content from web pages.
The Fetch MCP Server is designed to facilitate the retrieval and processing of web content by converting HTML into markdown format, making it easier for language models to consume. This server is particularly useful for applications that require reading and analyzing web pages in a structured manner. It includes a fetch tool that allows users to specify the starting point of content extraction, enabling models to read web pages in chunks. However, users should exercise caution as the server can access local/internal IP addresses, which may pose a security risk. The server can be installed using various methods, including uv, pip, and docker, and can be configured for different platforms like Claude.app and VS Code. Customization options include ignoring robots.txt, setting a custom user-agent, and using a proxy.
Features
- Fetches web content and converts it to markdown for easier consumption by LLMs.
- Allows content extraction in chunks using the start_index argument.
- Supports installation via uv, pip, and docker.
- Customizable user-agent and proxy settings.
- Obeys robots.txt by default, with an option to ignore it.
Tools
fetch
Fetches a URL from the internet and optionally extracts its contents as markdown.
Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.