Stop a database
AI agents invoke stop_database to trigger actions in Coolify MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a state-changing action on an external service (Coolify-managed database) that is not immediately reversible without manual intervention. While not permanently destructive (the database persists and can be restarted), stopping a production database causes immediate service downtime and application failures.
From the tool's definition Tool name: 'stop_database'; description: 'Stop a database'. This triggers an external operation (stopping a running database service) whose effects are immediate and consequential.
Attacks that exploit this kind of access
Stop a database. 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.
Register the Coolify MCP Server MCP server in PolicyLayer and add a rule for stop_database: 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.
stop_database is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_database 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.
Set action: deny in the PolicyLayer policy for stop_database. 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.
stop_database is provided by the Coolify MCP Server MCP server (pavelsukhachev/mcp-server-coolify). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →