git_checkout · GitHub MCP Server MCP: Risk & Policy

WHAT IT DOES

What git_checkout does on GitHub MCP Server

AI agents invoke git_checkout to trigger actions in GitHub 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.

WHY IT NEEDS A POLICY

Why git_checkout needs a policy

git_checkout can switch the active branch (changing HEAD and updating the working tree) or restore/overwrite working tree files from a commit. Both operations have significant side effects: switching branches can overwrite local changes, and restoring files overwrites current working tree content.

From the tool's definition 'Switches branches or restores working tree files' — branch switching and working tree restoration are active filesystem operations that alter repository state

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

git_checkout Rate-limited

git_checkout 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": {
    "git_checkout": {
      "limits": [
        {
          "counter": "git_checkout_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 GitHub MCP Server, so you can run agents against it safely.

FAQ

Questions about git_checkout

What does the git_checkout tool do? +

Switches branches or restores working tree files. It is categorised as a Execute tool in the GitHub 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 git_checkout? +

Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for git_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 GitHub MCP Server. Nothing to install.

What risk level is git_checkout? +

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

Can I rate-limit git_checkout? +

Yes. Add a rate_limit block to the git_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 git_checkout completely? +

Set action: deny in the PolicyLayer policy for git_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 git_checkout? +

git_checkout is provided by the GitHub MCP Server MCP server (lyderdev/github-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.