docker-exec

Execute a command in a running Docker container

SERVERDocker MCP Server SOURCE0xshariq/docker-mcp-server

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/0xshariq-docker-mcp-server/docker-exec.md

WHAT IT DOES

What docker-exec does on Docker MCP Server

AI agents invoke docker-exec 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.

RISK

Why docker-exec is rated High

The docker-exec tool allows running arbitrary commands inside running containers. This poses critical risk because: (1) commands are fully argument-dependent with unpredictable effects, (2) a misconfigured or compromised AI agent could execute destructive commands (rm -rf /, data exfiltration, credential theft), (3) containers often have access to sensitive data, environment variables, and internal networks, and (4)…

From the tool's definition Tool name 'docker-exec' and description 'Execute a command in a running Docker container' clearly indicate execution of arbitrary commands within container contexts.

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 Docker MCP Server, 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 Docker MCP Server, 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 command in a running Docker 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.

How do I enforce a policy on docker-exec? +

Register the Docker MCP Server 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 Docker MCP Server. 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 Docker MCP Server MCP server (0xshariq/docker-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Docker MCP Server, and thousands of servers like it.

This server

All 24 Docker MCP Server tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

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