exec
Executes arbitrary commands inside a running Docker container and returns structured output. WARNING: may execute untrusted code.
This record as markdown: /tools/io-github-dave-london-docker/exec.md
What exec does on Docker
AI agents invoke exec 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.
Why exec is rated High
This tool allows running arbitrary code/commands inside a Docker container, which is inherently an Execute operation with critical severity due to the unrestricted nature and the explicit warning about untrusted code execution. The blast radius is maximal: an AI agent could use this to compromise containerized systems, exfiltrate data, pivot to other systems, or cause operational disruption.
From the tool's definition 'Executes arbitrary commands inside a running Docker container' - the tool explicitly permits execution of arbitrary commands with no restrictions mentioned. The description includes 'WARNING: may execute untrusted code', confirming the Execute category.
Attacks that exploit this kind of access
The rule that runs exec safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Docker, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For exec, this is the rule to start with:
exec 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 Docker, apply this rule, and every exec call is checked against it from then on.
Questions about exec
Executes arbitrary commands inside a running Docker container and returns structured output. WARNING: may execute untrusted code. 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 exec: 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.
exec 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 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. 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 is provided by the Docker MCP server (@paretools/docker). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Docker, and thousands of servers like it.
Across the catalogue