deploy

THE RISK

High Risk

Why deploy needs a policy

Deployment executes code and infrastructure changes in external systems (application servers, orchestrators). While not permanently destructive (deployments can theoretically be rolled back), the immediate effects are irreversible command execution on live systems. This fits Execute rather than Write because it triggers automated operations beyond simple data creation.

From the tool's definition Tool description states it "Deploy an application or service" which triggers external operations (deployment pipelines, service updates). The sibling tools include start/stop/restart actions indicating this controls live infrastructure.

Documented attack patterns abuse exactly the kind of access deploy gives an agent:

POLICY

How to control deploy

PolicyLayer is an MCP gateway — it sits between your AI agents and Coolify MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for deploy:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "deploy": {
      "limits": [
        {
          "counter": "deploy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

deploy stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Coolify MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Coolify MCP Server tools

Execute restart-application Restart a specific application using its UUID. This stops and then starts the application, Execute start-application Start a specific application using its UUID. This initiates the application and makes it a Execute stop-application Stop a specific application using its UUID. This halts the application and makes it unavai Write update-application Update the settings of a specific application, such as health check configurations. This a Read get-application Retrieve detailed information about a specific application using its UUID. This includes t Read list-applications Fetch a list of all applications currently managed by Coolify. This provides an overview o Read list-databases Fetch a list of all databases managed by Coolify. This provides an overview of all databas Read list-deployments Retrieve a list of all running deployments in Coolify. This includes details about the dep

All 11 Coolify MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Coolify MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about deploy

What does the deploy tool do? +

Deploy an application or service using a tag or UUID. This allows you to deploy new versions or updates to your applications. It is categorised as a Execute tool in the Coolify MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on deploy? +

Register the Coolify MCP Server MCP server in PolicyLayer and add a rule for deploy: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Coolify MCP Server. Nothing to install.

What risk level is deploy? +

deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit deploy? +

Yes. Add a rate_limit block to the deploy rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block deploy completely? +

Set action: deny in the PolicyLayer policy for deploy. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides deploy? +

deploy is provided by the Coolify MCP Server MCP server (stumason/coolify-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Coolify MCP Server tool call.

Start from Coolify MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →