docker_compose
Run docker compose/docker-compose in a directory. Use for ps, logs, pull, up -d, restart, etc.
This record as markdown: /tools/mcp-control-plane/docker-compose.md
What docker_compose does on Mcp Control Plane
AI agents invoke docker_compose to trigger actions in Mcp Control Plane. 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.
Why docker_compose is rated High
This tool executes arbitrary docker-compose commands which can start, stop, restart, and manage Docker containers. While some operations (ps, logs, pull) are read-like, the tool explicitly enables 'up -d' and 'restart' which actively manipulate running container infrastructure. The blast radius is high: an agent could start malicious containers, disrupt services, or compromise the underlying host.
From the tool's definition Tool description states 'Run docker compose/docker-compose in a directory. Use for ps, logs, pull, up -d, restart, etc.' The verb 'Run' combined with docker-compose commands like 'up -d' (start containers), 'restart' (restart services), and 'pull' (fetch…
Attacks that exploit this kind of access
The rule that runs docker_compose safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Control Plane, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For docker_compose, this is the rule to start with:
docker_compose 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Control Plane, apply this rule, and every docker_compose call is checked against it from then on.
Questions about docker_compose
Run docker compose/docker-compose in a directory. Use for ps, logs, pull, up -d, restart, etc. It is categorised as a Execute tool in the Mcp Control Plane MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Control Plane MCP server in PolicyLayer and add a rule for docker_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 Mcp Control Plane. Nothing to install.
docker_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 docker_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 docker_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.
docker_compose is provided by the Mcp Control Plane MCP server (albertik322-sudo/mcp-control-plane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mcp Control Plane, and thousands of servers like it.
Across the catalogue