Calculator MCP Server
A feature-rich MCP server for mathematical calculations, scientific functions, unit conversions, financial metrics, and statistical analysis.
README
Calculator MCP Server (Python)
A feature-rich Model Context Protocol (MCP) server for mathematical calculations, scientific functions, unit conversions, financial metrics, and statistical analysis.
Built with Python 3.10+, the official mcp SDK (FastMCP), and sympy. Supports both stdio (Claude Desktop) and sse (Claude Web / Remote HTTP Connectors) transport modes.
🚀 Features & Exposed Tools
evaluate_math_expression: Evaluates custom mathematical expressions safely using SymPy (e.g.2 * (3 + 4),sqrt(144) + sin(pi / 2),log(100, 10),5^3).perform_arithmetic: Basic arithmetic (add,subtract,multiply,divide) on arrays of numbers.scientific_calculation: Powers, roots (sqrt,cbrt), factorials, logarithms (log,ln), and trigonometric functions (sin,cos,tan).convert_unit: Physical unit conversions (Length, Mass/Weight, Temperature, Volume, Time).financial_calculator: Simple interest, Compound interest, Loan EMI calculations, and Percentages.calculate_statistics: Summary statistics (mean,median,mode,variance,stdev,summary).
📦 Installation & Setup
-
Install Dependencies:
pip install -r requirements.txt pip install -e . -
Run Automated Unit Tests:
pytest
💻 1. Connecting to Claude Desktop (Stdio Mode)
Your claude_desktop_config.json has been automatically created at:
C:\Users\ADMIN\AppData\Roaming\Claude\claude_desktop_config.json
{
"mcpServers": {
"calculator": {
"command": "C:\\Users\\ADMIN\\AppData\\Local\\Programs\\Python\\Python312\\python.exe",
"args": [
"-m",
"calculator_mcp.server"
],
"env": {
"PYTHONPATH": "E:/mcp tutorials"
}
}
}
}
Usage in Claude Desktop:
- Fully exit and restart Claude Desktop.
- Open a chat and look for the 🔨 (hammer/tools icon) at the bottom right of the message bar.
- Ask Claude: "What is sqrt(144) + sin(pi / 2)?" or "Convert 100 degC to degF".
🌐 2. Connecting to Claude Web & Remote Web Clients (SSE HTTP Mode)
To run the Calculator MCP as a web HTTP service (for web-based platforms, web connectors, or remote AI agents):
-
Start the SSE Web Server:
python -m calculator_mcp.server --transport sse --port 8000 -
Web Client Configuration:
{ "mcpServers": { "calculator-web": { "serverUrl": "http://localhost:8000/sse" } } } -
Public Tunneling for Remote Web Apps (Optional): If your web client (like remote Claude Web) is hosted outside your local network, expose port 8000 using
ngrokorlocaltunnel:npx localtunnel --port 8000 # Or using ngrok: ngrok http 8000Then use the generated public HTTPS URL:
https://<your-subdomain>.loca.lt/ssein your Web MCP connector configuration.
🔍 Interactive Testing via Web Interface (MCP Inspector)
You can launch the official Model Context Protocol interactive Web Inspector UI to visually test all tools in your browser:
mcp dev calculator_mcp/server.py
Or via Node:
npx @modelcontextprotocol/inspector@0.4.1 python -m calculator_mcp.server
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.