You are a specialized assistant that generates HTML code for interactive markdown-based mind maps (markmaps). When a user sends you content, respond with a complete HTML document that displays their content as a markmap visualization.
If artifact tool is turned on, you can use the artifact.

Follow these requirements:
1. Use the markmap-autoloader library (version 0.18 or latest stable version)
2. Format the HTML exactly according to the template below
3. Replace the demo content in the template with the user's content, preserving their hierarchical structure
4. Maintain the markmap configuration options (maxWidth: 300, colorFreezeLevel: 2)
5. If the user doesn't provide markdown formatting (# for headings), format their content appropriately with main topics using # and subtopics using ##

Template to follow:

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta http-equiv="X-UA-Compatible" content="IE=edge" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Markmap</title>
    <style>
      svg.markmap {
        width: 100%;
        height: 100vh;
      }
    </style>
    <script src="https://cdn.jsdelivr.net/npm/markmap-autoloader@0.18"></script>
  </head>
  <body>
    <div class="markmap">
      <script type="text/template">
        ---
        markmap:
          maxWidth: 300
          colorFreezeLevel: 2
        ---

        # markmap

        ## Links

        - <https://markmap.js.org/>
        - [GitHub](https://github.com/markmap/markmap)

        ## Related

        - [coc-markmap](https://github.com/markmap/coc-markmap)
        - [gatsby-remark-markmap](https://github.com/markmap/gatsby-remark-markmap)

        ## Features

        - links
        - **inline** ~~text~~ *styles*
        - multiline
          text
        - `inline code`
        - Katex - $x = {-b \pm \sqrt{b^2-4ac} \over 2a}$
        - This is a very very very very very very very very very very very very very very very long line.
      </script>
    </div>
  </body>
</html>

Visualization options: (If formulas or symbols don’t display correctly, download the HTML file and open it in a browser.)

1. View the mindmap in artifacts (if available):

2. Render the HTML file as a mindmap:

{
  "mcpServers": {
    "mindmap": {
      "command": "uvx",
      "args": ["mindmap-mcp-server", "--return-type", "html"]
    }
  }
}

or

recommended:

{
  "mcpServers": {
    "mindmap": {
      "command": "uvx",
      "args": ["mindmap-mcp-server", "--return-type", "filePath"]
    }
  }
}

we use --return-type to specify the return type of the mindmap content, you can choose html or filePath according to your needs.
html will return the entire HTML content of the mindmap, which you can preview in your AI client's artifact;

filePath will save the mindmap to a file and return the file path,which you can open in your browser. It can save your tokens !

Using a specific Python file in this repository:

{
  "mcpServers": {
    "mindmap": {
      "command": "python",
      "args": ["/path/to/your/mindmap_mcp_server/server.py", "--return-type", "html"]
    }
  }
}

or

{
  "mcpServers": {
    "mindmap": {
      "command": "python",
      "args": ["/path/to/your/mindmap_mcp_server/server.py", "--return-type", "filePath"]
    }
  }
}

we use --return-type to specify the return type of the mindmap content, you can choose html or filePath according to your needs. see using `uvx` for more details.

First, you pull the image:

docker pull ychen94/mindmap-converter-mcp

Second, set the server:

{
  "mcpServers": {
    "mindmap-converter": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "-v", "/path/to/output/folder:/output", "ychen94/mindmap-converter-mcp:latest"]
    }
  }
}

⚠️ Replace /path/to/output/folder with an actual path on your system where you want to save mind maps, such as /Users/username/Downloads on macOS or C:\\Users\\username\\Downloads on Windows.

Tools Provided in the docker container The server provides the following MCP tools:

1. markdown-to-mindmap-content
   Converts Markdown to an HTML mind map and returns the entire HTML content.
   You don't use the args: -v and /path/to/output/folder:/output in the command docker.
   Parameters:
   • markdown (string, required): The Markdown content to convert
   • toolbar (boolean, optional): Whether to show the toolbar (default: true)
   Best for: Simple mind maps where the HTML content size isn't a concern. And you can use artifact in your AI client to preview the mindmap.
2. markdown-to-mindmap-file
   Converts Markdown to an HTML mind map and saves it to a file in the mounted directory.
   Parameters:
   • markdown (string, required): The Markdown content to convert
   • filename (string, optional): Custom filename (default: auto-generated timestamp name)
   • toolbar (boolean, optional): Whether to show the toolbar (default: true)
   Best for: Complex mind maps or when you want to save the tokens for later use.
   you can open the html file in your browser to view the mindmap. Also you can use the iterm-mcp-server or other terminals' mcp servers to open the file in your browser without interrupting your workflow.