Cloud MCP Calculator
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cloud MCP Calculatorcalculate (150 * 2.5) / 5"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cloud MCP Calculator: Student & Instructor Guide
This repository contains a cloud-deployable math tool server using the Model Context Protocol (MCP) via Server-Sent Events (SSE). This architecture allows students to connect their local local LLM agents (via VS Code Continue) to a centralized, instructor-managed tool.
Distributed Architecture
The following diagram shows how the system is distributed between the instructor's cloud infrastructure and the students' local machines.
graph TB
subgraph "Cloud Infrastructure (Instructor)"
VM[Cloud Virtual Machine]
Docker[Docker Container]
Uvicorn[Uvicorn / SSE Server]
CalcTool[Calculator Logic]
VM --> Docker
Docker --> Uvicorn
Uvicorn --> CalcTool
end
subgraph "Student Machine"
VSCode[VS Code + Continue]
LLM[Local LLM / Ollama]
NB[01_math_agent.ipynb]
end
VSCode -- "HTTP-SSE / Port 8080" --> Uvicorn
NB -- "Standard Logic" --> OpenAI[OpenAI / API]Related MCP server: Calculator MCP
Protocol Interaction Flow
When a student asks a math question, the following exchange occurs via the SSE protocol:
sequenceDiagram
participant S as Student (VS Code)
participant C as Cloud server (VM)
participant T as Calculator Tool
S->>C: GET /sse (Connect)
C-->>S: SSE Stream Opened
S->>C: POST /sse?sessionId=... (Initialize)
C-->>S: JSON-RPC (Capabilites & ServerInfo)
S->>C: POST /sse (tools/call: calculate)
C->>T: eval(expression)
T-->>C: Result (e.g., "42")
C-->>S: JSON-RPC Result
S->>S: Display "The answer is 42."Student Setup (config.yaml)
To connect to the cloud tool, update your ~/.continue/config.yaml as follows:
mcpServers:
- name: cloud-calc
type: sse
url: http://<YOUR-VM-PUBLIC-IP>:8080/sse
experimental:
autoExecuteTools: trueInstructor Setup (Makefile)
Use the provided Makefile on your VM to manage the service easily:
Command | Action |
| Builds the |
| Starts the server in background (detached) on port 8080. |
| Follows the live server logs (useful for debugging student connections). |
| Gracefully stops and removes the running container. |
VM Security Note:
Ensure your VM's Cloud Firewall (Security Group) allows Inbound TCP traffic on Port 8080.
Debug:
This server cannot be deployed
Maintenance
Related MCP Connectors
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
AI-callable calculators and engineering models with real formulas. No hallucinated math.
Related MCP Servers
- AlicenseCqualityDmaintenanceA Model Context Protocol server that enables LLMs to perform precise numerical calculations by evaluating mathematical expressions.12,609 PyPI157MIT
- AlicenseBqualityCmaintenanceA Model Context Protocol server that provides basic calculator functionality for LLMs, enabling them to perform mathematical operations like addition, subtraction, multiplication, division, modulo, and square root.6238 npm15MIT
- AlicenseNot gradedqualityDmaintenanceA tool server that processes mathematical expressions via Multi-Chain Protocol (MCP), allowing LLMs to solve math problems through tool integration.MIT
- -licenseNot gradedqualityNot gradedmaintenanceA calculator server that exposes mathematical functions as tools (add, subtract, multiply, divide, square, power, square root), enabling language models to perform calculations through Model Context Protocol (MCP).-