container_exec
Run a command in a container and return the results from stdout. If necessary, set a timeout. To debug, stream back standard error. If you
This record as markdown: /tools/cloudflare/container-exec.md
What container_exec does on Cloudflare
AI agents invoke container_exec to trigger actions in Cloudflare. 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 container_exec is rated High
The tool permits running arbitrary commands in a container, which can have unpredictable and severe side effects depending on what commands an AI agent chooses to execute. This is classic Execute category behavior. The critical severity reflects the ability to invoke any command (potentially destructive, exfiltrating data, or launching further attacks) without inherent safeguards mentioned in the description.
From the tool's definition Tool description states "Run a command in a container and return the results from stdout." This directly indicates execution of arbitrary commands within a container environment.
Attacks that exploit this kind of access
The rule that runs container_exec safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cloudflare, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For container_exec, this is the rule to start with:
container_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 Cloudflare, apply this rule, and every container_exec call is checked against it from then on.
Questions about container_exec
Run a command in a container and return the results from stdout. If necessary, set a timeout. To debug, stream back standard error. If you. It is categorised as a Execute tool in the Cloudflare MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cloudflare MCP server in PolicyLayer and add a rule for container_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 Cloudflare. Nothing to install.
container_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 container_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 container_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.
container_exec is provided by the Cloudflare MCP server (https://builds.mcp.cloudflare.com/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cloudflare, and thousands of servers like it.
Across the catalogue