xmind-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@xmind-mcp extract the 'Action Items' branch from workflow.xmind"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
xmind-mcp
一个用于解析和搜索 XMind 思维导图文件(.xmind)的 Model Context Protocol (MCP) 服务器。可以让 Claude 及其他 AI 应用高效地提取、搜索和处理思维导图数据,并支持 token 感知的格式化和智能错误处理。
快速开始
在 Claude Desktop 等客户端的配置中添加:
{
"mcpServers": {
"xmind-mcp": {
"command": "npx",
"args": [
"-y",
"@zengjing/xmind-mcp"
]
}
}
}Related MCP server: XMind Generator MCP
开发
构建
将 TypeScript 编译为 JavaScript:
npm run build不构建,仅做类型检查:
npm run lintAvailable Tools
3 toolsget_xmind_node_branchA
Extract a specific node and its subtree (up to specified depth) from an XMind file. Useful for large mind maps to avoid token overload by retrieving only relevant branches.
Inputs: path (required), nodeId (required), depth.
parse_xmindA
Parse an entire XMind document (.xmind file) and return formatted output (Markdown or JSON). Markdown format is more token-efficient and recommended for large documents. JSON format includes structure summary and detailed metadata. Supports both Zen (modern) and Legacy (XMind 8) formats.
Inputs: path (required), format.
search_xmind_nodesA
Search for nodes in an XMind file by keyword (title/notes) or label. Returns matching nodes with breadcrumb paths. Useful for large mind maps to find specific topics without loading entire document.
Inputs: path (required), query (required), searchIn, caseSensitive.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: parse the entire document, search nodes by keyword, and extract a specific branch. No ambiguity between these operations.
All tool names follow the consistent verb_noun snake_case pattern (parse_xmind, search_xmind_nodes, get_xmind_node_branch), making the API predictable.
Three tools is a well-scoped count for an XMind reading/exploration server. Each tool serves a distinct need without redundancy.
The tool set covers the full read-side lifecycle: full-document parsing, keyword search, and subtree extraction. There are no obvious gaps for the apparent purpose of exploring XMind files.
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Turn outlines and hierarchical notes into interactive mind maps through a hosted remote MCP server.
Hosted X (Twitter) MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
Related MCP Servers
- AlicenseDqualityDmaintenanceAn MCP server that allows LLMs to create structured Xmind mind maps with hierarchical topic structures, supporting features like notes, labels, and markers.159 npm46MIT
- AlicenseDqualityDmaintenanceAn MCP server that enables users to generate structured XMind mind maps with hierarchical topics, notes, and labels through natural language. It features automatic file saving to the local Documents folder and can automatically open generated maps in the XMind application.129 npm1MIT
- AlicenseBqualityDmaintenanceMCP server that visualizes Claude conversations as interactive mindmaps, enabling export and optional upload to Navigate Chat.213 npmMIT
- AlicenseAqualityDmaintenanceAn MCP server that lets Claude or ChatGPT read, create, and edit mind maps stored in a GitHub repository, with support for local and HTTP transport.8MIT