LLM SSE MCP Demo
This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time communication.
What is LLM SSE MCP Demo?
LLM SSE MCP Demo is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this project demonstrates the integration between llm clients and mcp (model context protocol) servers using server-sent events (sse) for real-time communication.
This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time communication.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This project demonstrates the integration between LLM client
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx llm-sse-mcp-demo-2025Configuration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LLM SSE MCP Demo
The LLM SSE MCP Demo 2025 is a hands-on reference implementation that demonstrates how to wire together LLM clients and MCP servers using Server-Sent Events (SSE) for real-time, streaming communication. It consists of three Spring Boot applications: an OAuth 2.0 authorization server, an SSE-based MCP server exposing math and time tools, and a web-based LLM chat client that routes user prompts through multiple AI providers including Claude, GPT, and Gemini. This project is aimed at Java developers who want to understand the full MCP transport layer and multi-LLM integration pattern.
Prerequisites
- Java 21 or higher with Gradle installed
- Docker and Docker Compose (for the observability stack)
- API keys for at least one supported LLM provider: ANTHROPIC_API_KEY, OPENAI_API_KEY, or Google Cloud credentials
- Ports 9000, 8080, and 10101 available on localhost
- An MCP-compatible client or the built-in web chat UI at http://localhost:10101
Start the observability stack
Launch the Docker Compose services for logging, tracing, and dashboards. These run in the background and are optional but recommended.
docker compose up -dStart the Authorization Server
Boot the OAuth 2.0 token management service on port 9000. This issues tokens that the LLM client uses to authenticate with the MCP server.
cd authorization-server-demo && ./gradlew bootRunStart the SSE MCP Server
Launch the Spring Boot MCP server on port 8080. It exposes four tools over SSE: sumNumbers, multiplyNumbers, getCurrentDateTime, and setAlarm.
cd sse-mcp-server-demo && ./gradlew bootRunSet LLM provider credentials
Export at least one LLM API key before starting the client. The client supports Anthropic Claude, OpenAI GPT, Google Gemini, and local Ollama models.
export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-...
# Or for Google:
export GOOGLE_PROJECT_ID=your-project-id
export GOOGLE_ZONE=us-central1Start the LLM Chat Client
Launch the web UI on port 10101. Open http://localhost:10101 in a browser to send prompts that will be routed through the MCP server.
cd llm-mcp-client-demo && ./gradlew bootRunOpen the chat UI and observability dashboards
Navigate to the chat interface to send prompts, and optionally check the Grafana dashboard for traces and logs.
# Chat UI:
open http://localhost:10101
# Observability (Grafana):
open http://localhost:3000LLM SSE MCP Demo Examples
Client configuration
Example MCP client configuration pointing to the SSE MCP server running on localhost:8080.
{
"mcpServers": {
"llm-sse-demo": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-sse", "http://localhost:8080/sse"]
}
}
}Prompts to try
Example prompts for the built-in chat UI or any connected MCP client to exercise the four exposed tools.
- "What is 5 times 4 plus 7?"
- "Add 123 and 456 together."
- "What is the current date and time?"
- "Set an alarm for 2025-06-01T09:00:00."Troubleshooting LLM SSE MCP Demo
Port already in use when starting one of the three services
Check for processes occupying ports 9000, 8080, or 10101 with 'lsof -i :8080'. Stop the conflicting process or change the port in the respective application.properties file.
LLM client cannot reach the MCP server
Ensure the SSE MCP server on port 8080 started successfully before launching the client. Check the Spring Boot log for 'Started SseMcpServerApplication' and verify the OAuth token endpoint on port 9000 is reachable.
API key not recognized or LLM calls fail
Confirm the environment variable is exported in the same shell session where you run './gradlew bootRun'. Alternatively, set the key in the application's application.yml or application.properties file under the relevant provider configuration block.
Frequently Asked Questions about LLM SSE MCP Demo
What is LLM SSE MCP Demo?
LLM SSE MCP Demo is a Model Context Protocol (MCP) server that this project demonstrates the integration between llm clients and mcp (model context protocol) servers using server-sent events (sse) for real-time communication. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install LLM SSE MCP Demo?
Follow the installation instructions on the LLM SSE MCP Demo GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with LLM SSE MCP Demo?
LLM SSE MCP Demo works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is LLM SSE MCP Demo free to use?
Yes, LLM SSE MCP Demo is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
LLM SSE MCP Demo Alternatives — Similar Developer Tools Servers
Looking for alternatives to LLM SSE MCP Demo? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up LLM SSE MCP Demo in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use LLM SSE MCP Demo?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.