思维导图mcp

yspdsh/mindmcp_0.2.13
Hosted
0 Stars 161 次浏览 风之痕 更新于 2026-08-23

Markmap MCP 服务器基于模型上下文协议(MCP),可以将 Markdown 文本一键转换为交互式思维导图。它支持丰富的交互操作,并可以导出多种图像格式。该服务器集成了阿里云 Qwen AI,支持 AI 生成思维导图,并且支持双存储(阿里云 OSS 和 Minio)以实现快速预览和长期存储。

MCP 服务配置

复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用

{
  "mcpServers": {
    "markmap": {
      "args": [
        "-y",
        "@jiushan93/markmap-mcp-server"
      ],
      "command": "npx",
      "env": {
        "DASHSCOPE_API_KEY": "sk-your-dashscope-api-key",
        "MINIO_ACCESS_KEY": "your-minio-access-key",
        "MINIO_SECRET_KEY": "your-minio-secret-key",
        "OSS_ACCESS_KEY_ID": "your-oss-access-key-id",
        "OSS_ACCESS_KEY_SECRET": "your-oss-access-key-secret"
      },
      "type": "stdio"
    }
  }
}

该服务需要配置环境变量:DASHSCOPE_API_KEY、MINIO_ACCESS_KEY、MINIO_SECRET_KEY、OSS_ACCESS_KEY_ID、OSS_ACCESS_KEY_SECRET

可用工具 (1 个)

该服务在 MCP 协议中暴露的工具,AI 可按需调用

text_to_mindmap 1 个参数 需填 1 项

Convert a text description into an interactive mind map using AI. The text will be processed by Qwen AI model to generate Markdown, then converted to a mind map and uploaded to OSS.

必填参数:text

服务介绍

Markmap MCP Server

Sample Mindmap

NPM Version
GitHub License
中文文档
Stars

Markmap MCP Server is based on the Model Context Protocol (MCP) that allows one-click conversion of Markdown text to interactive mind maps, built on the open source project markmap. The generated mind maps support rich interactive operations and can be exported in various image formats.

🎉 Explore More Mind Mapping Tools

Try MarkXMind - An online editor that creates complex mind maps using simple XMindMark syntax. It supports real-time preview, multi-format export (.xmind/.svg/.png), importing existing XMind files. Try it now!

Features

  • 🤖 AI-Powered Generation: Generate mind maps from plain text using Alibaba Cloud Qwen AI (NEW in v0.2.0)
  • 🌠 Markdown to Mind Map: Convert Markdown text to interactive mind maps
  • 🔗 Dual Storage Support: Upload to both Aliyun OSS and Minio, providing download and preview links (NEW in v0.2.8)
  • ☁️ Aliyun OSS Integration: Automatically upload generated mind maps to Aliyun Object Storage and get online access links
  • 🚀 Minio Fast Preview: Provide Minio preview links for fast access
  • 🖼️ Multi-format Export: Support for exporting as PNG, JPG, SVG images, and XMind-compatible format
  • 🔄 Interactive Operations: Support for zooming, expanding/collapsing nodes, and other interactive features
  • 📋 Markdown Copy: One-click copy of the original Markdown content
  • 🧹 Auto Cleanup: Automatically delete local temporary files after OSS upload

Prerequisites

  1. Node.js (v20 or above)

Installation

Manual Installation

# Install from npm
npm install @jiushan93/markmap-mcp-server -g

# Basic run
npx -y @jiushan93/markmap-mcp-server

# Specify output directory
npx -y @jiushan93/markmap-mcp-server --output /path/to/output/directory

Alternatively, you can clone the repository and run locally:

# Clone the repository
git clone https://github.com/jiushan-test/markmap-mcp.git

# Navigate to the project directory
cd markmap-mcp

# Build project
npm install && npm run build

# Run the server
node build/index.js

Usage

Configuration (AI and OSS Required)

⚠️ Important: This tool requires API keys from environment variables to work.

The following configurations are pre-configured in the code:

  • OSS Bucket: aiagenttest
  • OSS Region: oss-cn-beijing
  • OSS Endpoint: oss-cn-beijing.aliyuncs.com
  • Qwen Model: qwen3-235b-a22b-thinking-2507
  • API URL: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions

You need to provide the following API keys:

{
  "mcpServers": {
    "markmap": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@jiushan93/markmap-mcp-server"],
      "env": {
        "DASHSCOPE_API_KEY": "sk-your-dashscope-api-key",
        "OSS_ACCESS_KEY_ID": "your-oss-access-key-id",
        "OSS_ACCESS_KEY_SECRET": "your-oss-access-key-secret",
        "MINIO_ACCESS_KEY": "your-minio-access-key",
        "MINIO_SECRET_KEY": "your-minio-secret-key"
      }
    }
  }
}

[!IMPORTANT]

Environment Variables

Required API Keys (Must be configured):

  • DASHSCOPE_API_KEY or QWEN_API_KEY: Your Alibaba Cloud DashScope API key (Required)
  • OSS_ACCESS_KEY_ID: Aliyun OSS Access Key ID (Required)
  • OSS_ACCESS_KEY_SECRET: Aliyun OSS Access Key Secret (Required)
  • MINIO_ACCESS_KEY: Minio Access Key (Required)
  • MINIO_SECRET_KEY: Minio Secret Key (Required)

Pre-configured Settings (Hard-coded in the application):

  • Model: qwen3-235b-a22b-thinking-2507
  • API URL: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
  • OSS Bucket: aiagenttest
  • OSS Region: oss-cn-beijing
  • OSS Endpoint: oss-cn-beijing.aliyuncs.com
  • Minio Endpoint: 119.45.11.171
  • Minio Bucket: page
  • Minio Preview URL: http://page.thingotech.com.cn/page

Optional Configuration:

  • MARKMAP_DIR: Specify the output directory for temporary files (defaults to system temp directory)

⚠️ Important Notes:

  • Need to configure 5 API keys via environment variables (DashScope, OSS, Minio)
  • All other settings (buckets, regions, model, endpoints) are pre-configured
  • Mind maps are uploaded to both OSS and Minio, returning two links
  • OSS link valid for 5 years, Minio link for fast preview
  • Temporary local files are automatically deleted after upload

Available Tool

text-to-mindmap

Convert plain text descriptions into interactive mind maps using AI.

The text will be processed by Qwen AI model to generate structured Markdown, then converted to a mind map and automatically uploaded to OSS.

Parameters:

  • text: Text description to convert into a mind map (required string)

Example:

{
  "text": "Python programming basics"
}

Filename Generation Rules:

The system automatically extracts the first heading (# heading) from the generated Markdown as the filename:

  • Keeps only Chinese, English, and numeric characters
  • Limits length to 20 characters
  • Adds timestamp to avoid duplicates
  • Example: Pythonprogrammingbasics-1760693213328.html

Return Value:

On success, returns a structured JSON response (with two links):

{
  "success": true,
  "downloadUrl": "https://aiagenttest.oss-cn-beijing.aliyuncs.com/markmap/Python-programming-basics-1234567890.html?...",
  "previewUrl": "http://page.thingotech.com.cn/page/Python-programming-basics-1234567890.html",
  "filename": "Python-programming-basics-1234567890.html",
  "timestamp": "2025-10-17T07:45:30.123Z",
  "message": "✓ 思维导图生成成功!(OSS + Minio 双存储)\n\n📥 下载文件:\nhttps://aiagenttest.oss-cn-beijing.aliyuncs.com/markmap/Python-programming-basics-1234567890.html?...\n\n👁️ 在线预览:\nhttp://page.thingotech.com.cn/page/Python-programming-basics-1234567890.html\n\n📄 文件名:Python-programming-basics-1234567890.html\n\n💡 提示:复制上方链接到浏览器即可访问思维导图,支持缩放、展开/折叠、导出等交互操作。"
}

Field Descriptions:

  • downloadUrl: OSS download link (long-term valid, 5-year signed URL)
  • previewUrl: Minio preview link (fast access)
  • filename: Auto-generated filename (extracted from first heading, max 20 chars)
  • timestamp: Generation timestamp
  • message: Plain text formatted status message (URLs on separate lines for easy copying)

message Field Format:

✓ 思维导图生成成功!(OSS + Minio 双存储)

📥 下载文件:
https://aiagenttest.oss-cn-beijing.aliyuncs.com/markmap/Python-programming-basics-1234567890.html?...

👁️ 在线预览:
http://page.thingotech.com.cn/page/Python-programming-basics-1234567890.html

📄 文件名:Python-programming-basics-1234567890.html

💡 提示:复制上方链接到浏览器即可访问思维导图,支持缩放、展开/折叠、导出等交互操作。

On failure, returns error details:

{
  "success": false,
  "error": "OSS upload failed",
  "message": "思维导图已生成,但OSS上传失败",
  "localPath": "/path/to/local/file.html"
}

Requirements:

  • ✅ Qwen API configuration (required)
  • ✅ OSS configuration (required)

Available Export Formats:

The generated mind map HTML includes buttons (in Chinese) to export in multiple formats:

  • 📸 导出 PNG: Export as PNG image
  • 📸 导出 JPG: Export as JPG image
  • 📸 导出 SVG: Export as SVG vector image
  • 🧠 导出 .mm 文件: Export as FreeMind format (.mm file) - Can be opened in XMind, FreeMind, Freeplane
  • 📋 复制 Markdown: Copy the original Markdown content

License

This project is licensed under the MIT License.

相关 MCP 服务