Markmap MCP Server
Enables conversion of plain text descriptions and Markdown content into interactive mind maps using AI. Automatically uploads generated mind maps to Aliyun OSS and provides online access links.
README
Markmap MCP Server
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
- 🔗 URL Download Support: Download Markdown files directly from URLs for conversion
- ☁️ Aliyun OSS Integration: Automatically upload generated mind maps to Aliyun Object Storage and get online access links
- 🖼️ 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
- 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 only need to provide the 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"
}
}
}
}
[!IMPORTANT]
Environment Variables
Required API Keys (Must be configured):
DASHSCOPE_API_KEYorQWEN_API_KEY: Your Alibaba Cloud DashScope API key (Required)
- Get from: https://dashscope.console.aliyun.com/
OSS_ACCESS_KEY_ID: Aliyun OSS Access Key ID (Required)OSS_ACCESS_KEY_SECRET: Aliyun OSS Access Key Secret (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.comOptional Configuration:
MARKMAP_DIR: Specify the output directory for temporary files (defaults to system temp directory)⚠️ Important Notes:
- Only API keys need to be configured via environment variables
- All other settings (bucket, region, model) are pre-configured
- Mind maps are stored in OSS and return signed URLs (5-year validity)
- Temporary local files are automatically deleted after OSS 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"
}
Return Value:
On success, returns only the URL:
https://aiagenttest.oss-cn-beijing.aliyuncs.com/markmap/Python-programming-basics-1234567890.html?...
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.