GeoGebra MCP Server
Provides access to GeoGebra's mathematical computation, geometry construction, and visualization capabilities. Enables mathematical calculations, CAS operations, geometric constructions, and exporting results as PNG or PDF images.
README
GeoGebra MCP Server
A Model Context Protocol (MCP) server that provides access to GeoGebra's computation and drawing capabilities through a standardized interface.
Features
Computation Tools
- eval_command: Execute GeoGebra commands
- eval_command_cas: Computer Algebra System calculations
- math_calculation: Mathematical expression evaluation
- geometry_construction: Geometric constructions and property calculations
Drawing & Export Tools
- export_png: Export constructions as PNG images
- export_pdf: Export constructions as PDF documents
- set_xml: Load constructions from XML
- get_xml: Get current construction as XML
- refresh_views: Refresh all views
Installation
- Install dependencies:
cd mcp-geogebra
npm install
- Make the server executable:
chmod +x src/index.js
Configuration
Add to your MCP client configuration (e.g., for Claude Code):
{
"mcpServers": {
"geogebra": {
"command": "node",
"args": ["/path/to/mcp-geogebra/src/index.js"],
"env": {
"GEOGEBRA_BASE_URL": "http://localhost:3000"
}
}
}
}
Usage Examples
Basic Math Calculation
// Calculate integral of x^2 from 0 to 1
{
"name": "math_calculation",
"arguments": {
"expression": "Integral(x^2, 0, 1)"
}
}
CAS Calculation
// Solve quadratic equation
{
"name": "eval_command_cas",
"arguments": {
"command": "Solve(x^2 - 4 = 0, x)",
"rounding": "2"
}
}
Geometry Construction
// Create triangle and get area
{
"name": "geometry_construction",
"arguments": {
"construction": "A=(0,0); B=(4,0); C=(0,3); poly1=Polygon(A,B,C)",
"properties": ["area", "perimeter"]
}
}
Export Image
// Export as high-quality PNG
{
"name": "export_png",
"arguments": {
"exportScale": 2.0,
"transparent": true,
"dpi": 600
}
}
API Reference
eval_command
Execute a GeoGebra command.
Parameters:
command(string): GeoGebra command to execute
Example: "f(x)=x^2; Integral(f,0,1)"
eval_command_cas
Execute CAS command with precision control.
Parameters:
command(string): CAS commandrounding(string): Rounding precision (default: "2")
Example: "Solve(x^3 - 2x + 1 = 0, x)"
export_png
Export construction as PNG image.
Parameters:
exportScale(number): Scale factor (default: 1.0)transparent(boolean): Transparent background (default: false)dpi(number): Resolution (default: 300)greyscale(boolean): Greyscale output (default: false)
export_pdf
Export construction as PDF document.
Parameters:
scale(number): Scale factor (default: 1.0)filename(string): Output filenamedpi(number): Resolution (default: 72)
math_calculation
Evaluate mathematical expressions.
Parameters:
expression(string): Math expressionvariables(object): Variable values
Example:
{
"expression": "a^2 + b^2",
"variables": {"a": 3, "b": 4}
}
geometry_construction
Create geometric constructions and get properties.
Parameters:
construction(string): Construction commandsproperties(array): Properties to calculate
Supported properties: area, perimeter, coordinates
Environment Variables
GEOGEBRA_BASE_URL: Base URL of GeoGebra server (default: http://localhost:3000)
Development
Project Structure
mcp-geogebra/
├── src/
│ ├── index.js # Main server entry point
│ ├── tools.js # Tool definitions
│ └── geogebra-client.js # GeoGebra API client
├── package.json
└── README.md
Adding New Tools
- Define tool in
src/tools.js - Add handler method in
src/index.js - Implement client method in
src/geogebra-client.js
Testing
Run the server directly:
npm start
License
MIT License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。