checkout

Switches branches or restores files. Returns structured data with ref, previous ref, whether a new branch was created, and detached HEAD status. Pass

SERVERDocker SOURCE@paretools/docker

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-docker/checkout.md

WHAT IT DOES

What checkout does on Docker

AI agents use checkout to create or update resources in Docker, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docker environment.

RISK

Why checkout is rated Medium

This tool modifies the Git repository state reversibly—it changes branches, restores files, and can create branches. These are Write operations (create/update with side effects) rather than Read (would be query-only) or Destructive (changes are reversible via another checkout/reset). The blast radius is medium: misuse could overwrite uncommitted work or switch to an unintended branch, but the damage is reversible.

From the tool's definition 'Switches branches or restores files' indicates modification of repository state and working directory contents. The tool can create new branches ('whether a new branch was created') and change HEAD position ('detached HEAD status').

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs checkout 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 checkout, this is the rule to start with:

checkout Rate-limited

checkout stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "checkout": {
      "limits": [
        {
          "counter": "checkout_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about checkout

What does the checkout tool do? +

Switches branches or restores files. Returns structured data with ref, previous ref, whether a new branch was created, and detached HEAD status. Pass. It is categorised as a Write tool in the Docker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on checkout? +

Register the Docker MCP server in PolicyLayer and add a rule for checkout: 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.

What risk level is checkout? +

checkout is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit checkout? +

Yes. Add a rate_limit block to the checkout 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 checkout completely? +

Set action: deny in the PolicyLayer policy for checkout. 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 checkout? +

checkout 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.

KEEP EXPLORING

More on Docker, and thousands of servers like it.

This server

All 202 Docker tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →