// MCP TOOL REFERENCE

COOLIFY TOOLS

26 tools from the Coolify MCP Server, categorised by risk level.

// ALL 26 COOLIFY TOOLS

READ 15 tools

Read get_current_team Get current team details Read get_current_team_members Get current team members Read get_deployment Get deployment details Read get_server_domains Get server domains Read get_server_resources Get server resource usage Read get_team Get details of a specific team Read get_version Get Coolify version information Read health_check Check Coolify API health status Read list_applications List all applications Read list_deployments List all deployments Read list_private_keys List all private keys Read list_servers List all servers Read list_services List all services Read list_teams List all teams Read validate_server Validate server configuration

WRITE 4 tools

Write create_application Create a new application Write create_private_key Create a new private key Write create_server Create a new server Write create_service Create a new service

EXECUTE 7 tools

Execute execute_command_application Execute command in application container Execute restart_application Restart an application Execute restart_service Restart a service Execute start_application Start an application Execute start_service Start a service Execute stop_application Stop an application Execute stop_service Stop a service

// RUNNING THIS SERVER

The managed route: connect Coolify through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y coolify-mcp-server

// FAQ

How many tools does the Coolify MCP server have? +

The Coolify MCP server exposes 26 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Coolify tools? +

Route the Coolify server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Coolify tools fall into? +

Coolify tools are categorised as Read (15), Write (4), Execute (7). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.