mcp-fetch
If you are the rightful owner of mcp-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@mcphub.com.
Fetch MCP Server is a Model Context Protocol server that provides web content fetching capabilities, enabling LLMs to retrieve and process content from web pages.
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 and analyze. The server allows for the extraction of web page content in chunks, using the `start_index` argument to specify where to begin content extraction. This feature is particularly useful for models that need to read large web pages incrementally until they find the necessary information. The server can be installed using Node.js for a more robust HTML simplification process or via PIP for Python environments.
Features
- Web content fetching: Retrieve and process web pages by converting HTML to markdown.
- Chunked content extraction: Use `start_index` to read web pages in segments.
- Markdown conversion: Simplifies HTML content for easier consumption by LLMs.
- Optional raw content: Fetch raw HTML content without markdown conversion.
- Flexible installation: Available via Node.js or PIP for different environments.
Tools
fetch
Crawl content from a web page and convert it to Markdown format
