Skip to main content
Glama

VLLM MCP Server

by StanleyChanH
docker-compose.yml1.39 kB
version: '3.8' services: vllm-mcp: build: . container_name: vllm-mcp-server ports: - "8080:8080" environment: # OpenAI Configuration - OPENAI_API_KEY=${OPENAI_API_KEY} - OPENAI_BASE_URL=${OPENAI_BASE_URL:-https://api.openai.com/v1} # Dashscope Configuration - DASHSCOPE_API_KEY=${DASHSCOPE_API_KEY} # Server Configuration - VLLM_MCP_HOST=0.0.0.0 - VLLM_MCP_PORT=8080 - VLLM_MCP_TRANSPORT=http - VLLM_MCP_LOG_LEVEL=${LOG_LEVEL:-INFO} # Optional: Custom config - VLLM_MCP_CONFIG_PATH=/app/config.json volumes: - ./config.json:/app/config.json:ro - ./logs:/app/logs restart: unless-stopped healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8080/health"] interval: 30s timeout: 10s retries: 3 start_period: 40s networks: - vllm-mcp-network # Optional: Add nginx reverse proxy for production nginx: image: nginx:alpine container_name: vllm-mcp-nginx ports: - "80:80" - "443:443" volumes: - ./nginx.conf:/etc/nginx/nginx.conf:ro - ./ssl:/etc/nginx/ssl:ro depends_on: - vllm-mcp restart: unless-stopped networks: - vllm-mcp-network profiles: - production networks: vllm-mcp-network: driver: bridge volumes: logs: driver: local

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/StanleyChanH/vllm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server