MCP for Math and MacOS operation
What is rohinigaonkar mcp math macos
Introduction to MCP; Draw & Add Text to Keynote on MacOS
This project implements a math agent using Model Control Protocol (MCP) that can perform mathematical calculations and present results visually in Keynote on macOS. The agent can draw shapes and add text to Keynote slides, making it useful for creating mathematical presentations.
Features
- Mathematical operations (addition, subtraction, multiplication, division, etc.)
- Advanced mathematical functions (factorial, logarithms, trigonometric functions)
- ASCII value calculations and exponential sum operations
- Visual presentation in Keynote:
- Drawing rectangles
- Adding text to slides
- Automatic slide management
Prerequisites
- Python 3.x
- macOS (for Keynote integration)
- Keynote installed on your system
- Google Gemini API key
Installation
- Clone the repository:
git clone <your-repository-url>
cd keynote-drawing-text
- Install required dependencies:
pip install -r requirements.txt
- Create a
.env
file in the project root and add your Gemini API key:
GEMINI_API_KEY=your_api_key_here
Project Structure
mcp-server.py
: Contains the server implementation with mathematical tools and Keynote integrationmcp-client.py
: Implements the client that communicates with the LLM and manages the workflowrequirements.txt
: Lists all Python dependencies
Usage
The client script (mcp-client.py
) automatically handles the MCP server startup and communication. You only need to run the client with your query:
python mcp-client.py "Your mathematical query here"
For example:
python mcp-client.py "Find the ASCII values of characters in INDIA and then return sum of exponentials of those values"
If no query is provided, the script will use a default query mentioned in the above example.
The client will:
- Automatically start the MCP server in the background
- Open Keynote and create a new document
- Perform the requested mathematical operations
- Draw a rectangle on the slide
- Add the result as text within the rectangle
Note: The MCP server is managed internally by the client script, so you don't need to start it manually. The server handles all the mathematical operations and Keynote interactions, while the client manages the communication with the language model and orchestrates the overall workflow.
Available Mathematical Tools
-
Basic Operations:
- Addition (
add
) - Subtraction (
subtract
) - Multiplication (
multiply
) - Division (
divide
) - Power (
power
) - Square root (
sqrt
) - Cube root (
cbrt
)
- Addition (
-
Advanced Operations:
- Factorial (
factorial
) - Natural logarithm (
log
) - Remainder (
remainder
) - Trigonometric functions (
sin
,cos
,tan
) - Fibonacci sequence (
fibonacci_numbers
) - ASCII value calculations (
strings_to_chars_to_int
) - Exponential sum (
int_list_to_exponential_sum
)
- Factorial (
Keynote Integration
The project includes tools for Keynote integration:
mac_open_keynote
: Opens Keynote and creates a new documentmac_draw_rectangle
: Draws a rectangle on the current slidemac_add_text_in_keynote
: Adds text to the current slide
Error Handling
The system includes comprehensive error handling for:
- API communication issues
- Invalid mathematical operations
- Keynote integration problems
- Timeout handling for LLM responses
Tools
- Model Control Protocol (MCP) for the framework
- Google Gemini for the language model
- Apple Keynote for the presentation platform
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
zhixiaoqiang desktop image manager mcp
MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
Submit Your MCP Server
Share your MCP server with the community
Submit Now