drawio-parser-mcp
Validates and parses Draw.io XML syntax, enabling analysis and verification of diagram structures, especially for AI-generated content.
README
Draw.io Parser MCP Server
一个用于验证和分析 Draw.io XML 语法的 MCP (Model Context Protocol) 服务器,专为检查 AI 生成的 Draw.io 图表内容设计。
功能特性
- 语法验证 - 检查 Draw.io XML 的语法正确性,发现错误和警告
- 结构解析 - 解析图表结构,提取单元格、边、图层等信息
- 图表分析 - 完整分析图表,同时返回验证结果和结构信息
- 摘要统计 - 快速获取图表统计信息(形状数、连接数等)
- 单元格查询 - 列出所有单元格或按 ID 查找特定单元格
安装
使用 uv (推荐)
# 克隆项目
git clone https://github.com/dabian321/pyDrawioParserMCP.git
cd pyDrawioParserMCP
# 安装依赖
uv sync
使用 pip
pip install -e .
MCP 配置
将以下配置添加到你的 MCP 配置文件 (如 Claude Desktop 的 mcp.json):
{
"mcpServers": {
"drawio-parser-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/pyDrawioParserMCP",
"run",
"drawio-parser-mcp"
],
"env": {
"PYTHONIOENCODING": "utf-8"
}
}
}
}
将
/path/to/pyDrawioParserMCP替换为项目实际路径
MCP 工具
| 工具名 | 描述 |
|---|---|
validate_drawio |
验证 Draw.io XML 语法和结构,返回错误、警告和建议 |
parse_drawio |
解析 Draw.io XML,提取单元格、边、图层和统计信息 |
analyze_drawio |
完整分析:同时执行验证和解析 |
get_diagram_summary |
获取图表摘要统计信息 |
list_cells |
列出图表中所有单元格(形状和连接) |
find_cell |
按 ID 查找特定单元格 |
命令行使用
# 启动 MCP 服务器 (stdio 模式)
drawio-parser-mcp
# 验证单个文件
drawio-parser-mcp --check mydiagram.drawio
# 启用详细日志
drawio-parser-mcp -v
使用示例
验证 AI 生成的 Draw.io 内容
from drawio_parser_mcp import DrawioValidator
validator = DrawioValidator()
xml_content = """
<mxfile>
<diagram id="test" name="Page-1">
<mxGraphModel>
<root>
<mxCell id="0"/>
<mxCell id="1" parent="0"/>
<mxCell id="2" value="Hello" style="rounded=1;" vertex="1" parent="1">
<mxGeometry x="100" y="100" width="120" height="60" as="geometry"/>
</mxCell>
</root>
</mxGraphModel>
</diagram>
</mxfile>
"""
result = validator.validate(xml_content)
print(f"Valid: {result.valid}")
print(f"Errors: {result.error_count}, Warnings: {result.warning_count}")
解析图表结构
from drawio_parser_mcp import DrawioParser
parser = DrawioParser()
structure = parser.parse(xml_content)
print(f"Pages: {len(structure.pages)}")
print(f"Total shapes: {structure.total_vertices}")
print(f"Total connections: {structure.total_edges}")
项目结构
pyDrawioParserMCP/
├── src/drawio_parser_mcp/
│ ├── __init__.py # 包入口
│ ├── cli.py # 命令行接口
│ ├── server.py # MCP Server 实现
│ ├── parser.py # XML 解析器
│ ├── validator.py # 语法验证器
│ └── models.py # 数据模型
├── tests/ # 测试文件
├── architecture.drawio # 架构图
└── pyproject.toml # 项目配置
验证规则
| 错误代码 | 描述 |
|---|---|
XML_SYNTAX_ERROR |
XML 语法错误 |
INVALID_ROOT |
无效的根元素 |
NO_DIAGRAM |
缺少 diagram 元素 |
MISSING_ROOT_CELL |
缺少 id="0" 的根单元格 |
MISSING_DEFAULT_PARENT |
缺少 id="1" 的默认父单元格 |
INVALID_PARENT |
引用了不存在的父单元格 |
INVALID_EDGE_SOURCE |
边的源单元格不存在 |
INVALID_EDGE_TARGET |
边的目标单元格不存在 |
NEGATIVE_WIDTH/HEIGHT |
负数的宽度或高度 |
依赖
- Python >= 3.10
- mcp >= 1.0.0
- pydantic >= 2.0.0
- lxml >= 5.0.0
开发
# 安装开发依赖
uv sync --extra dev
# 运行测试
pytest
# 代码格式检查
ruff check src/
License
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.