loading…
Весь каталог
101 Example
БесплатноA foundational implementation of a Model Context Protocol (MCP) server designed for educational purposes. It demonstrates the complete interaction between an LL
автор: behavioral-ds
Описание
A foundational implementation of a Model Context Protocol (MCP) server designed for educational purposes. It demonstrates the complete interaction between an LLM, an inference engine, and a client during an agentic call.
README
Calling a tool
- Make sure that nothing is listening on ports
8000and8080. Open 3 generously sized terminals on your screen. - Download a sensible model. Qwen 3.5 4B is sensible.
- Compile fresh
llama.cpp:git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp cmake -B build && cmake --build build --config Release -j 6 - Launch the llama in terminal #1:
./llama-server -m ~/Downloads/Qwen3.5-4B-Q8_0.gguf --ctx-size 4096 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.00 --verbose --webui-mcp-proxy - Clone this repository:
https://github.com/behavioral-ds/mcp-example && cd mcp-example - Install deps:
poetry install && poetry shell - Launch MCP in terminal #2:
python mcp_serve.py - Execute the Agentic Call™ in terminal #3:
python call.py - Observe the dance between
LLM <-> Inference engine <-> MCP <-> Client.
Using MCP prompts
Open llama web UI at http://localhost:8080/, go to settings and add a new MCP server:
Select "MCP prompt" when drafting a new message:
That's your
@mcp.prompt()parsed into UI element, click it:...and supply some meaningful content:
Then click "Use prompt" and rejoice:
Как установить
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"mcp-101-example": {
"command": "npx",
"args": []
}
}
}