What runtime dependencies does Demo MCP Basic require?
Node.js version 23.0 or higher and npm (bundled with Node.js). A Google AI API key (for Gemini) or a Vertex AI project ID is required.
Demo MCP Basic
@bertrandgressier
Basic information
About Demo MCP Basic
Demo of MCP server with HTTP SSE and a client
Demo MCP Basic config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryDemo MCP Basic tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Demo MCP Basic?
Demo MCP Basic demonstrates a fundamental client‑server interaction using the Model Context Protocol (MCP). The server provides simple calculation tools (addition, subtraction, etc.) and the client, using the AI SDK, connects a Google AI model (Gemini/Vertex AI) to those tools, enabling the AI to call external functionalities during text generation.
How to use Demo MCP Basic?
Clone the repository, install dependencies (npm install), and create a .env file with your Google AI API key or Vertex AI project ID. Build the project with npm run build, then start the server (npm run start:server) and the client (npm run start:client). Development modes are available via npm run dev:server and npm run dev:client.
Key features of Demo MCP Basic
- Offers basic arithmetic tools (addition, subtraction) via MCP.
- Connects Google Gemini or Vertex AI models to external tools.
- Client‑server architecture with SSE transport on localhost:3001.
- Includes both production and development run scripts.
- Fully typed TypeScript project with automatic compilation.
Use cases of Demo MCP Basic
- Extending AI models with custom calculation tools.
- Prototyping MCP‑based tool integrations for AI applications.
- Learning how to implement an MCP client and server.
- Demonstrating secure, local tool invocation from an AI model.
Frequently asked questions
How does the client communicate with the server?
The client connects to the server via SSE (Server‑Sent Events) at `http://localhost:3001/sse`.
What tools does the server provide?
The server exposes simple calculation tools, specifically addition and subtraction (and potentially other basic arithmetic operations).
Where does the application data live?
All configuration (API keys, project IDs) is stored locally in a `.env` file. No external databases are used; the server runs locally and communicates with Google’s AI services over HTTPS.
Are there any known limitations?
The server only offers basic arithmetic tools. The client is a demonstration script hard‑coded to evaluate `"6 + 12"` and relies on the AI model correctly invoking the tool. No authentication or secure transport beyond SSE is implemented.
More Other MCP servers
Klarix Intelligence Engine
KlarixB2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
ICSS
chokcoco不止于 CSS
20.7K
P
PickFu MCP
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
26.0K
Handl
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments