MCP Client Demo
@yonaka15
About MCP Client Demo
A demo implementation of a Model Context Protocol (MCP) client using Web Workers and Server-Sent Events (SSE).
Overview
What is MCP Client Demo?
MCP Client Demo is a work-in-progress demo implementation of a Model Context Protocol (MCP) client using Web Workers and Server-Sent Events (SSE). It is built with Vite + React and TypeScript, intended for developers to test and explore MCP client-server communication.
How to use MCP Client Demo?
Ensure Node.js 18.x or later is installed and an MCP-compatible server is running on localhost:3020. Clone the repository, run npm install, then npm run dev to start the development server. Open test.html in a browser, click “Connect” to establish a connection, use “List Tools” to see available tools, select a tool, provide input in JSON format, and click “Execute Tool” to run it.
Key features of MCP Client Demo
- Web Worker-based MCP client implementation
- Server-Sent Events (SSE) transport
- Interactive testing UI
- Type-safe implementation with TypeScript
- Built with Vite + React
Use cases of MCP Client Demo
- Demonstrating how an MCP client communicates with a server over SSE
- Testing available tools from an MCP server in a browser interface
- Learning the MCP protocol through hands-on interaction
FAQ from MCP Client Demo
Is MCP Client Demo production-ready?
No. The project is currently a work in progress (WIP); features and implementations may change significantly.
What MCP servers does MCP Client Demo support?
It works with any MCP-compatible server that communicates over SSE and runs on localhost:3020.
What are the prerequisites to run MCP Client Demo?
Node.js 18.x or later and a running MCP server on localhost:3020 are required.
Can I use MCP Client Demo with a different server host or port?
The README does not specify configuration options; the demo is hardcoded to localhost:3020.
How do I execute a tool in the demo?
After connecting, click “List Tools”, select a tool, enter its input in JSON format, and click “Execute Tool”.
Basic information
More Agent Frameworks MCP clients
Evo AI - AI Agents Platform
evolutionapiEvo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.
Ollama MCP (Model Context Protocol)
mihirrdMCP client for local ollama models
MCP CLI client
adhikaspA simple CLI to run LLM prompt and implement MCP client.
MCP CLI - Model Context Protocol Command Line Interface
chrishayukn8n-nodes-mcp-client
nerding-ion8n custom node for MCP
Comments