Huoshui MCP Server

An MCP server that provides tools for fetching, converting, and extracting data from web pages.

Local serverstdioPython

What is the Huoshui MCP server?

If you already use Huoshui, the huoshui mcp server is the piece that lets your assistant work with it directly. An MCP server that provides tools for fetching, converting, and extracting data from web pages.

Installation

The server ships on PyPI as git, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • fetch_url — Fetch content from URLs with customizable timeout, redirect handling, and user-agent
  • fetch_with_headers — Fetch URLs with custom headers for authenticated requests
  • html_to_markdown_tool — Convert HTML to clean Markdown format
  • html_to_text_tool — Extract plain text from HTML
  • clean_html_tool — Remove scripts/styles and sanitize HTML
  • json_to_markdown_tool — Convert JSON data to readable Markdown
  • extract_article_tool — Extract main article content using readability
  • extract_links_tool — Extract all links with filtering options
  • extract_metadata_tool — Extract page metadata (title, description, OG tags)
  • extract_images_tool — Extract images with size filtering
  • extract_structured_data_tool — Extract JSON-LD and microdata
  • Features — See PUBLISHING.md for detailed documentation

Credentials and setup notes

  • Python 3.11+ - Dependencies listed in pyproject.toml

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Huoshui.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Huoshui's toolset — fetch_url, fetch_with_headers, html_to_markdown_tool and 9 more — is a fair guide to whether it matches your workflow. It is maintained by huoshuiai42; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Huoshui's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
fetch_urlFetch content from URLs with customizable timeout, redirect handling, and user-agent
fetch_with_headersFetch URLs with custom headers for authenticated requests
html_to_markdown_toolConvert HTML to clean Markdown format
html_to_text_toolExtract plain text from HTML
clean_html_toolRemove scripts/styles and sanitize HTML
json_to_markdown_toolConvert JSON data to readable Markdown
extract_article_toolExtract main article content using readability
extract_links_toolExtract all links with filtering options
extract_metadata_toolExtract page metadata (title, description, OG tags)
extract_images_toolExtract images with size filtering
extract_structured_data_toolExtract JSON-LD and microdata
FeaturesSee [PUBLISHING.md](PUBLISHING.md) for detailed documentation.

How to install the Huoshui MCP server

{
  "mcpServers": {
    "huoshui-fetch": {
      "command": "uvx",
      "args": ["--no-cache", "--from", ".", "huoshui-fetch"],
      "cwd": "/path/to/huoshui-fetch"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.11+ - Dependencies listed in pyproject.toml

Example prompts to try

  • Use Huoshui to fetch url.
  • Use Huoshui to fetch with headers.
  • Use Huoshui to html to markdown tool.

Frequently asked questions

It connects Huoshui to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (fetch_url, fetch_with_headers, html_to_markdown_tool, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Huoshui directly.