@processon/mcp-server-processon

@processon/mcp-server-processon

Converts structured Markdown into ProcessOn mind maps via API, enabling AI agents and tools to create mind maps programmatically.

Category
Visit Server

README

@processon/mcp-server-processon

🚀 基于 MCP 协议的 Markdown → ProcessOn 思维导图生成工具。

该工具可将结构化 Markdown 内容转化为符合 ProcessOn 要求的树状图结构,并通过 API 创建思维导图文件,适用于大模型 Agent、Cherry Studio 等场景。


✨ 功能特性

  • ✅ 支持结构化 Markdown 转思维导图
  • ✅ 自动调用 ProcessOn API 创建文件
  • ✅ 基于 MCP 协议,可直接集成大模型工具链
  • ✅ 支持 check() 工具验证密钥与服务连通性
  • ✅ 支持 npx 运行,无需全局安装

📦 安装方式

首次运行时会自动安装 Python 依赖。请确保系统已安装 Python(推荐 3.8+)并添加到 PATH。

✅ 方式一:使用 npx(推荐)

npx @processon/mcp-server-processon

✅ 方式二:全局安装

npm install -g @processon/mcp-server-processon

运行服务:

@processon/mcp-server-processon

🔧 环境变量配置

服务通过环境变量读取 ProcessOn 配置信息:

变量名 是否必须 说明
PROCESSON_API_KEY ✅ 是 你的 ProcessOn API 密钥(可在 www.processon.com 账户中心 获取)
BASE_URL ❌ 否 自定义 API 地址(默认使用官方地址)

设置示例

macOS / Linux

export PROCESSON_API_KEY=YOU PROCESSON_API_KEY

Windows(CMD)

set PROCESSON_API_KEY="YOU PROCESSON_API_KEY"

Windows(PowerShell)

$env:PROCESSON_API_KEY="YOU PROCESSON_API_KEY"

🚀 使用说明

启动服务

npx @processon/mcp-server-processon

或(已全局安装):

@processon/mcp-server-processon

默认以 stdio 模式启动 MCP 服务。


查看版本

npx @processon/mcp-server-processon --version

🛠 MCP 工具接口

本服务通过 MCP 协议提供以下两个方法:


🧪 check()

用于验证 API KEY 是否已配置,并返回当前连接的 API 地址。

请求示例:

{
  "tool": "check",
  "args": {}
}

返回示例:

"https://www.processon.com:your_api_key"

🧠 createProcessOnMind(title, content)

根据 Markdown 内容生成思维导图。

请求参数:

参数名 类型 必填 说明
title string 思维导图文件名
content string Markdown 内容

Markdown 内容格式要求:

  • # 一级标题:作为导图根节点
  • ## 二级标题及以下:作为子节点,支持到 ######

示例请求:

{
  "tool": "createProcessOnMind",
  "args": {
    "title": "项目计划",
    "content": "# 项目计划\n## 阶段一\n### 任务 1\n### 任务 2\n## 阶段二\n### 任务 3"
  }
}

返回示例:

{
  "code": 0,
  "msg": "成功",
  "chartId": "abc123def456",
  "fileUrl": "https://www.processon.com/mindmap/abc123def456"
}

🐍 Python 依赖说明

系统将自动安装以下依赖:

  • httpx >= 0.24.0
  • pydantic >= 1.10.0
  • fastmcp >= 0.1.3
  • 更多依赖包请参考requirements.txt文件

如需手动安装:

pip install -r requirements.txt

🧑‍💻 本地调试方式

你也可以在本地手动启动 MCP 服务:

cd py
export PROCESSON_API_KEY=your_token
python processon.py --transport stdio

🍒 在 Cherry Studio 中使用本 MCP 服务

打开Cherry Studio,左下角的设置,选择MCP服务器,右上角添加服务器,选择从JSON导入

在文件中添加如下内容后保存

"processon_mind": {
  "name": "ProcessOn_CreateMind",
  "type": "stdio",
  "description": "ProcessOn创建思维导图",
  "isActive": true,
  "registryUrl": "",
  "command": "npx",
  "args": [
    "@processon/mcp-server-processon"
  ],
  "env": {
    "PROCESSON_API_KEY": "{YOU PROCESSON_API_KEY}"
  }
}


📁 项目结构说明

mcp-server-processon/
├── bin/
│   └── cli.js              # Node 启动脚本,供 npx 使用
├── py/
│   └── processon.py        # Python 实现的 MCP Server
├── requirements.txt        # Python 依赖清单
├── package.json            # npm 包配置
└── README.md               # 使用说明文档

📄 协议 License

MIT License © 2025 琪天大圣

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured