AI agents invoke deploy-compose to trigger actions in Docker. 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.
This tool triggers external operations (Docker daemon commands) that instantiate and configure running services. While not immediately destructive (containers can be stopped), the deployment itself has significant side effects: network creation, volume allocation, service initialization, and resource consumption. Misuse could spawn unintended services, expose ports, or allocate resources maliciously.
From the tool's definition Tool name 'deploy-compose' and description 'Deploy a Docker Compose stack' indicate execution of infrastructure operations.
Attacks that exploit this kind of access
Deploy a Docker Compose stack. It is categorised as a Execute tool in the Docker MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docker MCP server in PolicyLayer and add a rule for deploy-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 Docker. Nothing to install.
deploy-compose 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 deploy-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 deploy-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.
deploy-compose is provided by the Docker MCP server (quantgeekdev/docker-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 →