xmind-generator
An MCP (Model Context Protocol) server for generating Xmind mind maps. This server allows LLMs to create structured mind maps through the MCP protocol.
claude mcp add --transport stdio bangyizhang-xmind-generator-mcp node path/to/xmind-generator-mcp/dist/index.js \ --env outputPath="/path/to/save/xmind/files" \ --env autoOpenFile="false"
How to use
The Xmind Generator MCP Server exposes tools that let you create structured Xmind mind maps or export existing maps as Markdown outlines through the MCP protocol. The core tool, generate-mind-map, accepts a hierarchical structure of topics including titles, notes, labels, markers, and child topics to produce a finished .xmind file saved to a specified output path. You can also read a .xmind file and export its outline as Markdown using read-mind-map. The server is designed to integrate with Claude Desktop and other MCP clients, so you can invoke these tools directly from chat conversations or automated workflows. When using generate-mind-map, you can specify an overall title for the mind map, provide nested topics with optional notes and metadata, declare relationships between topics, and control where the resulting file is stored via outputPath. The read-mind-map tool enables parsing of an existing .xmind file to a Markdown outline for quick viewing or documentation.
To use these capabilities, configure the MCP server in your Claude Desktop setup (or your MCP client of choice) with the xmind-generator server, then call generate-mind-map or read-mind-map with the appropriate JSON payloads. If you supply outputPath in the tool call, it overrides the environment variable for where the file is saved.
How to install
Prerequisites:
- Node.js v18 or higher
- npm or pnpm
- Xmind desktop application (for opening generated mind maps)
- Claude Desktop (for easy integration with Claude workflows)
Install and build (local development):
-
Clone the repository: git clone https://github.com/BangyiZhang/xmind-generator-mcp.git cd xmind-generator-mcp
-
Install dependencies: npm install
-
Build the MCP server (if the project uses a build step): npm run build
-
Run the server locally (example): node dist/index.js
Claude Desktop configuration (example, to be placed in claude_desktop_config.json): Option 1 (npx, recommended for quick start): { "mcpServers": { "xmind-generator": { "command": "npx", "args": ["xmind-generator-mcp"], "env": { "outputPath": "/path/to/save/xmind/files", "autoOpenFile": "false" } } } }
Option 2 (local installation): { "mcpServers": { "xmind-generator": { "command": "node", "args": ["path/to/xmind-generator-mcp/dist/index.js"], "env": { "outputPath": "/path/to/save/xmind/files", "autoOpenFile": "false" } } } }
Additional notes
Environment variables are optional but helpful. The env block can set:
- outputPath: Default directory for saved Xmind files. You can override per-call by providing outputPath in the tool payload.
- autoOpenFile: If set to "false", generated files won’t auto-open after creation. Default is typically true. Be sure to replace path placeholders with real paths on your machine. The generate-mind-map tool supports a hierarchical topics array with titles, optional notes, labels, and markers, plus an optional relationships array to define connections between topics. The read-mind-map tool expects an inputPath to a .xmind file and can export in style A (outline) by default. If you encounter permission or file-not-found errors, verify that the outputPath directory exists and your user account has write access.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.