Skip to main content
Glama

CodeAlive MCP

Official
by CodeAlive-AI
docker-compose.example.yml3.83 kB
version: '3.8' services: codealive-mcp: # Use the latest stable image from GitHub Container Registry image: ghcr.io/codealive-ai/codealive-mcp:main # Container name for easy reference container_name: codealive-mcp-server # Restart policy - automatically restart if container stops restart: unless-stopped # Port mapping - expose MCP server on port 8000 ports: - "8000:8000" # Environment variables environment: # ========================================== # CONFIGURATION FOR SELF-HOSTED CODEALIVE # ========================================== # Uncomment and set this to your self-hosted CodeAlive instance URL # REQUIRED for self-hosted deployments # CODEALIVE_BASE_URL: "https://codealive.yourcompany.com" # ========================================== # CONFIGURATION FOR CODEALIVE CLOUD # ========================================== # For CodeAlive Cloud, comment out or remove CODEALIVE_BASE_URL above # The server will use the default: https://app.codealive.ai # ========================================== # API KEY CONFIGURATION (IMPORTANT!) # ========================================== # In HTTP mode, API keys should be provided by clients via # "Authorization: Bearer YOUR_KEY" headers, NOT environment variables. # # Do NOT set CODEALIVE_API_KEY here in production. # Each client connection should provide their own API key. # ========================================== # OPTIONAL SETTINGS # ========================================== # Enable debug mode (verbose logging) # DEBUG_MODE: "false" # Disable SSL verification (only for development/testing) # CODEALIVE_IGNORE_SSL: "false" # Command to run the MCP server in HTTP mode command: > python src/codealive_mcp_server.py --transport http --host 0.0.0.0 --port 8000 # Health check configuration healthcheck: test: ["CMD-SHELL", "curl -f http://localhost:8000/health || exit 1"] interval: 30s timeout: 5s retries: 3 start_period: 10s # Resource limits (adjust based on your needs) deploy: resources: limits: cpus: '0.5' memory: 512M reservations: cpus: '0.25' memory: 256M # ========================================== # USAGE INSTRUCTIONS # ========================================== # # 1. Copy this file to docker-compose.yml: # cp docker-compose.example.yml docker-compose.yml # # 2. Edit docker-compose.yml: # - For self-hosted: Uncomment and set CODEALIVE_BASE_URL # - For cloud: Leave CODEALIVE_BASE_URL commented out # # 3. Start the service: # docker compose up -d # # 4. Check health: # curl http://localhost:8000/health # # 5. Connect AI clients using: # - URL: http://your-server:8000/api # - Header: Authorization: Bearer YOUR_API_KEY # # ========================================== # EXAMPLES # ========================================== # # Claude Code: # claude mcp add --transport http codealive http://localhost:8000/api \ # --header "Authorization: Bearer YOUR_API_KEY" # # Cursor/Other Clients (JSON config): # { # "mcpServers": { # "codealive": { # "url": "http://localhost:8000/api", # "headers": { # "Authorization": "Bearer YOUR_API_KEY" # } # } # } # } # # ========================================== # TROUBLESHOOTING # ========================================== # # View logs: # docker compose logs -f codealive-mcp # # Restart service: # docker compose restart codealive-mcp # # Stop service: # docker compose down # # Update to latest version: # docker compose pull # docker compose up -d

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/CodeAlive-AI/codealive-mcp'

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