容器管理服务器

# Clone or navigate to project
cd podman-mcp-server

# Install dependencies
uv sync

# Or with pip:
pip install -r requirements.txt

# Transport mode
MCP_TRANSPORT=http                    # http, streamable-http, or stdio (default)

# Server settings
MCP_HOST=0.0.0.0                     # Binding host
MCP_PORT=3001                         # Server port
MCP_SERVER_NAME=Podman MCP Server    # Display name

# Broadcasting (for MCP Discovery Hub)
MCP_ENABLE_BROADCAST=true            # Enable/disable broadcasting
MCP_BROADCAST_INTERVAL=30            # Seconds between announcements

MCP_TRANSPORT=http
MCP_PORT=3001
MCP_SERVER_NAME=Podman MCP Server
MCP_ENABLE_BROADCAST=true
MCP_BROADCAST_INTERVAL=30

# Using environment variables
MCP_TRANSPORT=http MCP_PORT=3001 uv run main.py

# Or with .env file
uv run main.py

MCP_TRANSPORT=streamable-http MCP_PORT=3001 uv run main.py

# Default mode, works with Claude Desktop
uv run main.py

list_containers(all: bool = False)

{
  "method": "tools/call",
  "params": {
    "name": "list_containers",
    "arguments": { "all": true }
  }
}

container_info(container: str)

start_container(container: str)

stop_container(container: str, timeout: int = 10)

restart_container(container: str)

container_logs(container: str, tail: int = 100)

run_container(
  image: str,
  name: str = None,
  detach: bool = True,
  ports: List[str] = [],
  env: List[str] = [],
  volumes: List[str] = []
)

{
  "method": "tools/call",
  "params": {
    "name": "run_container",
    "arguments": {
      "image": "nginx:latest",
      "name": "my-webserver",
      "ports": ["8080:80"],
      "detach": true
    }
  }
}

remove_container(container: str, force: bool = False)

exec_container(container: str, command: List[str])

container_stats(container: str = None, no_stream: bool = True)

list_images(all: bool = False)

pull_image(image: str)

# Scan for the server manually
curl -X POST http://localhost:8000/scan \
  -H "Content-Type: application/json" \
  -d '{"ports": [3001]}'

curl http://localhost:3001/

{
  "name": "Podman MCP Server",
  "version": "1.0.0",
  "protocol": "MCP Streamable HTTP",
  "endpoint": "/mcp"
}

"User: Start a new web server and configure it"
AI: I'll start an nginx container for you...
→ calls run_container(image="nginx", name="webserver", ports=["8080:80"])

"User: What's the status of my database container?"
AI: Let me check the logs and stats...
→ calls container_logs(container="postgres", tail=50)
→ calls container_stats(container="postgres")

Host 1: Podman MCP Server (port 3001)
Host 2: Podman MCP Server (port 3001)
Host 3: MCP Discovery Hub (port 8000)
        ↓
        All containers managed from single AI interface

"User: Set up a development database for testing"
AI: I'll create a PostgreSQL container for you...
→ calls run_container(
    image="postgres:15",
    name="dev-db",
    env=["POSTGRES_PASSWORD=devpass"]
  )

# View logs
tail -f podman_mcp.log

# Check for errors
grep ERROR podman_mcp.log

# Use a different port
MCP_PORT=3002 uv run main.py

# Verify multicast is enabled
ip route show

# Check firewall
sudo firewall-cmd --add-service=mdns --permanent

# Start Podman service
systemctl start podman

# Verify connection
podman ps