AI agents invoke docker_container_start to trigger actions in Infra Ops. 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 executes external operations (container startup) that can have significant side effects. While not permanently destructive like deletion, container start commands can trigger arbitrary workloads, scripts, or services defined in the container image.
From the tool's definition Tool name 'docker_container_start' and description 'Start a stopped Docker container' indicate execution of container operations.
Attacks that exploit this kind of access
Start a stopped Docker container. It is categorised as a Execute tool in the Infra Ops MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Infra Ops MCP server in PolicyLayer and add a rule for docker_container_start: 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 Infra Ops. Nothing to install.
docker_container_start 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_container_start 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_container_start. 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_container_start is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →