docker_proxy · Portainer MCP: Risk & Policy

WHAT IT DOES

What docker_proxy does on Portainer MCP

AI agents invoke docker_proxy to trigger actions in Portainer MCP. 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 IT NEEDS A POLICY

Why docker_proxy needs a policy

A Docker proxy tool typically forwards requests to the Docker daemon, enabling a wide range of operations from read-only queries to running arbitrary containers or destructive actions. Given the breadth of the Docker API (which includes running containers, executing commands inside containers, deleting images/volumes/networks), the most severe plausible category is Execute (potentially Destructive).

From the tool's definition Tool name 'docker_proxy' suggests proxying Docker API calls, which can include executing containers, modifying images, and destructive operations. Description is empty, providing no further detail.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

docker_proxy Rate-limited

docker_proxy 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "docker_proxy": {
      "limits": [
        {
          "counter": "docker_proxy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Portainer MCP, so you can run agents against it safely.

FAQ

Questions about docker_proxy

What does the docker_proxy tool do? +

docker_proxy. It is categorised as a Execute tool in the Portainer MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on docker_proxy? +

Register the Portainer MCP server in PolicyLayer and add a rule for docker_proxy: 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 Portainer MCP. Nothing to install.

What risk level is docker_proxy? +

docker_proxy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit docker_proxy? +

Yes. Add a rate_limit block to the docker_proxy 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.

How do I block docker_proxy completely? +

Set action: deny in the PolicyLayer policy for docker_proxy. 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.

What MCP server provides docker_proxy? +

docker_proxy is provided by the Portainer MCP server (portainer/portainer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.