What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to Large Language Models (LLMs).

What is the UBOS MCP Calculator Server?

The UBOS MCP Calculator Server is a specific implementation of an MCP server that provides basic arithmetic operations (add, subtract, multiply, divide) through a REST API. It can be deployed in Smithery and other environments.

What are the key features of the UBOS MCP Calculator Server?

Key features include basic arithmetic operations, MCP-compliant API endpoints, JSON schema validation, error handling, multiple communication modes (HTTP, WebSocket, stdio), and specialized entry points for different deployment scenarios.

How do I install the UBOS MCP Calculator Server?

1. Create a virtual environment.
2. Install dependencies using pip install -r requirements.txt.

What are the different deployment modes?

• HTTP Mode: Recommended for production and container environments.
• Smithery Mode: For local tool integration with Smithery.
• Dual Mode: For development and testing (not recommended for production).

How do I run the server in HTTP mode?

Set the environment variable MCP_HTTP_MODE=1 and run uvicorn server:app --host 0.0.0.0 --port 8000.

How do I run the server in Smithery mode?

Set the environment variable MCP_STDIO_MODE=1 and run python server.py.

What are the API endpoints?

• GET /health: Health check.
• GET /tools: List available tools and schemas.
• POST /: JSON-RPC endpoint for MCP protocol.
• POST /mcp: Dedicated MCP-compatible JSON-RPC endpoint for Smithery integration.

How does the server handle errors?

The server provides clear error messages for invalid operations, division by zero, insufficient operands, invalid parameter types, and JSON-RPC protocol errors.

How do I integrate the server with Smithery?

For local tool integration, use stdio mode with the MCP_STDIO_MODE=1 and LOGGING_CONFIG=stdio environment variables. For remote tool integration, use HTTP mode with the dedicated /mcp endpoint.

Can I deploy the server in a Docker container?

Yes, you can build and run the Docker container using docker build -t mcp-calculator-server . and docker run -p 8000:8000 mcp-calculator-server.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with LLM models, and create Multi-Agent Systems.

How does the UBOS MCP Calculator Server integrate with the UBOS Platform?

The server provides AI agents within the UBOS platform with the ability to perform arithmetic calculations as part of their decision-making processes, enhancing their capabilities and expanding their potential applications.