Demo MCP
About
Demo: mcp protocol with simple client and server file
Details
- Author
- josx
- GitHub stars
- 2
- Downloads
- 443
- Categories
- Other, AI
Jump to
- Drop-in setup with Python virtual environment and requirements
- Two server modes: plain and JWT‑authenticated
- Integrated demo client over SSE transport
- LangChain/LangGraph host integration with Ollama models
- Debug using the official MCP Inspector tool
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Demo MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, create a Python virtual environment, install dependencies with pip install -r requirements.txt, then run either python server.py for a plain server or python server_asgi.py for a server with JWT authentication. Use python client.py http://localhost:8000/sse to run the demo client, or python host_langchain.py <model> <ollama-url> to run a LangChain/LangGraph host.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"demo mcp": {
"mcp_demo": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"mcp_demo": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}Demo MCP
Info
- Server - Using server examples from modelcontextprotocol/python-sdk - Client - Using code from slavashvets/mcp-http-client-example - Debug - Using InspectorSetup
python3 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txt
Run Server
> You can use any of this two servers -python server.py or with jwt auth python server_asgi.py
Run demo client
-python client.py http://localhost:8000/sse
Run demo host (langchain/langgraph)
> You need to run ollama and download a model -python host_langchain.py llama3.3 http://localhost:11434
Debug
> You can debug server with this app - Open a new terminal and runnpx @modelcontextprotocol/inspector
- Point browser to http://127.0.0.1:6274
- Change Transport Type to SSE
- Change URL to http://localhost:8000/sse
- Press Connect and start testing serverSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
