SSE Calculator MCP Server
A stateful calculator server using Server-Sent Events for real-time communication, enabling AI assistants to perform calculations with session management and history tracking.
README
SSE Calculator MCP Server
A stateful calculator server that uses Server-Sent Events (SSE) for real-time communication. This server implements the Model Context Protocol (MCP) for integration with AI assistants.
Features
- Real-time calculator operations using SSE
- Stateful sessions for ongoing calculations
- History tracking for all calculations
- Web-based calculator interface
- MCP integration for AI assistants
Architecture
The server is built using NestJS and implements the following components:
- Session Service: Manages calculator sessions and state
- Calculator Service: Performs calculation operations
- SSE Controller: Handles client connections and event streaming
Getting Started
Prerequisites
- Node.js (v14 or higher)
- npm (v6 or higher)
Installation
- Clone the repository
- Install dependencies:
npm install
- Start the server:
npm run start:dev
- Open the calculator interface in your browser:
http://localhost:3000
API Endpoints
SSE Stream
GET /calculator/stream
Establishes an SSE connection and creates a new calculator session.
Calculate
POST /calculator/calculate/:sessionId
Performs a calculation operation on the specified session.
Request body:
{
"operation": "add", // add, subtract, multiply, divide, clear
"a": 5,
"b": 3
}
History
GET /calculator/history/:sessionId
Retrieves the calculation history for the specified session.
Sessions
GET /calculator/sessions
Retrieves all active calculator sessions.
MCP Integration
To use this server as an MCP server, add the following configuration to your MCP settings file:
{
"mcpServers": {
"remote-calculator": {
"url": "http://localhost:3000/calculator/stream",
"disabled": false,
"alwaysAllow": [],
"timeout": 60
}
}
}
Deployment Options
For production deployment, you can use the following options:
-
Docker: A Dockerfile is provided for containerized deployment
- See
Dockerfileanddocker-compose.ymlfor configuration
- See
-
Smithery.ai: Deploy directly from GitHub
- See
SMITHERY_DEPLOYMENT.mdfor detailed instructions - Configuration provided in
smithery.json
- See
-
Heroku/DigitalOcean: Cloud platform deployment
- See
DEPLOYMENT.mdfor step-by-step instructions
- See
-
Self-hosted: Use NGINX or similar for SSL termination and load balancing
Hosting Your Own MCP Server
After deploying your server, update your MCP client configuration to point to your hosted URL:
{
"mcpServers": {
"remote-calculator": {
"url": "https://your-deployed-url.com/calculator/stream",
"disabled": false,
"alwaysAllow": [],
"timeout": 60
}
}
}
License
MIT
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.