Execute a command in a running container
AI agents invoke exec_container to trigger actions in Docker 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.
This tool allows running arbitrary commands inside a Docker container, which is a classic Execute operation. The blast radius is high because an AI agent with this capability could run destructive commands, access sensitive data, or compromise container security depending on the container's contents and permissions.
From the tool's definition Tool name is 'exec_container' and description states 'Execute a command in a running container'. The term 'Execute' combined with 'command' in a running container indicates arbitrary code execution.
Attacks that exploit this kind of access
Execute a command in a running container. It is categorised as a Execute tool in the Docker MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docker MCP Server MCP server in PolicyLayer and add a rule for exec_container: 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 MCP Server. Nothing to install.
exec_container 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 exec_container 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 exec_container. 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.
exec_container is provided by the Docker MCP Server MCP server (swartdraak/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 →