docker_exec

Execute a shell command inside a Docker container.

SERVERMcp Control Plane SOURCEalbertik322-sudo/mcp-control-plane

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/mcp-control-plane/docker-exec.md

WHAT IT DOES

What docker_exec does on Mcp Control Plane

AI agents invoke docker_exec to trigger actions in Mcp Control Plane. 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.

RISK

Why docker_exec is rated High

This tool runs arbitrary shell commands within Docker containers, which can have wide-ranging side effects depending on what commands are executed. It is inherently high-risk because: (1) shell commands can modify files, install software, exfiltrate data, or compromise container isolation; (2) a misdirected or malicious command could affect multiple services; (3) the blast radius depends entirely on container…

From the tool's definition Tool name is 'docker_exec' and description states it will 'Execute a shell command inside a Docker container.' The verb 'execute' combined with 'shell command' confirms this is code/command execution.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs docker_exec safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Control Plane, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For docker_exec, this is the rule to start with:

docker_exec Rate-limited

docker_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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Control Plane, apply this rule, and every docker_exec call is checked against it from then on.

FAQ

Questions about docker_exec

What does the docker_exec tool do? +

Execute a shell command inside a Docker container. It is categorised as a Execute tool in the Mcp Control Plane 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_exec? +

Register the Mcp Control Plane MCP server in PolicyLayer and add a rule for docker_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 Mcp Control Plane. Nothing to install.

What risk level is docker_exec? +

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

Can I rate-limit docker_exec? +

Yes. Add a rate_limit block to the docker_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.

How do I block docker_exec completely? +

Set action: deny in the PolicyLayer policy for docker_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.

What MCP server provides docker_exec? +

docker_exec is provided by the Mcp Control Plane MCP server (albertik322-sudo/mcp-control-plane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Control Plane, and thousands of servers like it.

This server

All 286 Mcp Control Plane tools → High-risk tools on this server →

Across the catalogue

bash_exec on 0sec → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →