SSE Calculator
A stateful calculator server using Server-Sent Events (SSE) for real-time communication.
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
相關伺服器
Jane
A knowledge management server for stdlib and specs documents, with a configurable storage path.
OneNote MCP
An MCP server for Microsoft OneNote that supports personal notebooks and caches credentials for authentication.
Anki MCP
A MCP server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.
Propbar
UK property data: crime stats, schools, demographics, valuations, comparables, Ofsted ratings
MCP Email Verify
Validate email addresses using the AbstractAPI Email Validation API.
PromptX
An AI capability enhancement system providing professional roles, memory management, and knowledge systems for applications like Claude and Cursor.
Memory Pickle MCP
A project management and session memory tool for AI agents to track projects, tasks, and context during chat sessions.
Linear
Query and search for issues in Linear, a project management tool.
Canvas
Integrates with the Canvas Learning Management System (LMS), supporting FERPA-compliant anonymization and privacy controls.
macOS Defaults
Read and write macOS user defaults and settings.