LLM SSE MCP Demo MCP Server

This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time

Local serverstdio

What is the LLM SSE MCP Demo MCP server?

Most AI and media services work still happens through a UI a human drives. LLM SSE MCP Demo MCP server moves it into the conversation instead. This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time communication.

The short version

This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time communication. It consists of three Spring Boot applications that showcase OAuth 2.0 security, tool calling capabilities with various LLM models, and secure authentication services.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What it needs from you

Configuration is passed through the environment: ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_PROJECT_ID, GOOGLE_ZONE. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Java 17 or higher - Gradle - API keys for cloud LLM providers (optional) - Ollama installed locally (for local models) - Docker & Docker Compose

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by nlinhvu; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Configuration

  • Java 17 or higher - Gradle - API keys for cloud LLM providers (optional) - Ollama installed locally (for local models) - Docker & Docker Compose
VariableDescriptionRequired
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
GOOGLE_PROJECT_IDConfiguration value read at startup.Optional
GOOGLE_ZONEConfiguration value read at startup.Optional

Frequently asked questions

Anthropic Claude (claude-sonnet-4-20250514), OpenAI (o4-mini-2025-04-16), Google Gemini (gemini-2.5-flash-preview-05-20), and Ollama (qwen3:8b locally).