# create_service

Create a one-click or custom service. Provide either

Agent View of the PolicyLayer registry record for `create_service`. HTML page: https://policylayer.com/tools/coolify/create-service

## Facts

- Tool: `create_service`
- Server: Coolify (`coolify-mcp-server`) — https://policylayer.com/tools/coolify.md
- Install: `npx -y coolify-mcp-server`
- Homepage: git+https://github.com/wrediam/coolify-mcp-server.git
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_service",
    "arguments": {}
  }
}
```

## Why create_service is rated Medium

This tool creates new services, which is a reversible Write operation. It modifies the system state by adding new services but does not execute arbitrary code, delete data, or move money. However, the severity is high because creating services in an infrastructure platform like Coolify could have significant downstream effects on system resources and configurations, making misuse by an AI agent potentially impactful.

From the tool's own definition: "Tool name is 'create_service' and description states 'Create a one-click or custom service', indicating it creates new service resources."

## Use case

AI agents use create_service to create or update resources in Coolify, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Coolify environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Coolify:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_service": {
      "limits": [
        {
          "counter": "create_service_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Coolify (110)

- `delete_application` — Destructive — https://policylayer.com/tools/coolify/delete-application.md
- `delete_application_env` — Destructive — https://policylayer.com/tools/coolify/delete-application-env.md
- `delete_application_scheduled_task` — Destructive — https://policylayer.com/tools/coolify/delete-application-scheduled-task.md
- `delete_application_storage` — Destructive — https://policylayer.com/tools/coolify/delete-application-storage.md
- `delete_cloud_token` — Destructive — https://policylayer.com/tools/coolify/delete-cloud-token.md
- `delete_database` — Destructive — https://policylayer.com/tools/coolify/delete-database.md
- `delete_database_env` — Destructive — https://policylayer.com/tools/coolify/delete-database-env.md
- `delete_environment` — Destructive — https://policylayer.com/tools/coolify/delete-environment.md
- `delete_github_app` — Destructive — https://policylayer.com/tools/coolify/delete-github-app.md
- `delete_private_key` — Destructive — https://policylayer.com/tools/coolify/delete-private-key.md
- `delete_project` — Destructive — https://policylayer.com/tools/coolify/delete-project.md
- `delete_server` — Destructive — https://policylayer.com/tools/coolify/delete-server.md
- `delete_service` — Destructive — https://policylayer.com/tools/coolify/delete-service.md
- `delete_service_env` — Destructive — https://policylayer.com/tools/coolify/delete-service-env.md
- `delete_service_scheduled_task` — Destructive — https://policylayer.com/tools/coolify/delete-service-scheduled-task.md
- `disable_api` — Destructive — https://policylayer.com/tools/coolify/disable-api.md
- `cancel_deployment` — Execute — https://policylayer.com/tools/coolify/cancel-deployment.md
- `deploy_by_tag_or_uuid` — Execute — https://policylayer.com/tools/coolify/deploy-by-tag-or-uuid.md
- `enable_api` — Execute — https://policylayer.com/tools/coolify/enable-api.md
- `restart_application` — Execute — https://policylayer.com/tools/coolify/restart-application.md
- `restart_database` — Execute — https://policylayer.com/tools/coolify/restart-database.md
- `restart_service` — Execute — https://policylayer.com/tools/coolify/restart-service.md
- `start_application` — Execute — https://policylayer.com/tools/coolify/start-application.md
- `start_database` — Execute — https://policylayer.com/tools/coolify/start-database.md
- `start_service` — Execute — https://policylayer.com/tools/coolify/start-service.md
- `stop_application` — Execute — https://policylayer.com/tools/coolify/stop-application.md
- `stop_database` — Execute — https://policylayer.com/tools/coolify/stop-database.md
- `stop_service` — Execute — https://policylayer.com/tools/coolify/stop-service.md
- `get_application` — Read — https://policylayer.com/tools/coolify/get-application.md
- `get_application_logs` — Read — https://policylayer.com/tools/coolify/get-application-logs.md
- …and 80 more: https://policylayer.com/tools/coolify.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=coolify · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/coolify