AI agents use dokploy_update_compose to create or update resources in Dokploy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dokploy environment.
This tool modifies compose stack configuration, which is a Write operation (creates or modifies data reversibly). Severity is high because misconfigured compose stacks can impact deployed applications, services, and infrastructure—an AI agent could introduce breaking changes to production services.
From the tool's definition Tool name 'dokploy_update_compose' and description 'Update compose stack config fields' explicitly indicate modification of configuration data.
Attacks that exploit this kind of access
Update compose stack config fields. Only composeId is required; all other fields are optional. It is categorised as a Write tool in the Dokploy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dokploy MCP server in PolicyLayer and add a rule for dokploy_update_compose: 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 Dokploy. Nothing to install.
dokploy_update_compose is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dokploy_update_compose 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 dokploy_update_compose. 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.
dokploy_update_compose is provided by the Dokploy MCP server (wyattjoh/dokploy-mcp). 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 →