A Cuda Enabled MCP Agent for your LLM to conduct it's own Nvidia compiling and testing
1.0K
This loaded MCP enabled container will enable your LLM to attempt to compile, learn and develop it's own Cuda applications. Agentic Server Primer: Llama.cpp MCP Lesson 10: mcp-coder - Cuda Version
#!/bin/bash
CONTAINER_NAME="mcp-coder"
# Cleanup previous container
docker stop $CONTAINER_NAME 2>/dev/null
docker rm $CONTAINER_NAME 2>/dev/null
# Ensure workspace directory exists
mkdir -p ~/mcp-workspace
chmod -R 755 ~/mcp-workspace
# Pull latest version
docker pull cnmcdee/mcp-coder:latest
# Start container
docker run -d \
--name $CONTAINER_NAME \
--restart unless-stopped \
-p 5011:5011 \
-v ~/mcp-workspace:/work_path \
--env PYTHONUNBUFFERED=1 \
cnmcdee/mcp-coder:latest
echo "✅ MCP Coder container started successfully!"
echo "🌐 Access URL: http://localhost:5011/mcp"
echo "📋 Logs: docker logs -f $CONTAINER_NAME" ```
Content type
Image
Digest
sha256:0559abadb…
Size
3.5 GB
Last updated
5 months ago
docker pull cnmcdee/mcp-coder