checkpoint_restore · Rr MCP: Risk & Policy

WHAT IT DOES

What checkpoint_restore does on Rr

AI agents invoke checkpoint_restore to trigger actions in Rr. 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 checkpoint_restore needs a policy

Restoring a checkpoint modifies the live state of a debugging session by rewinding/replaying execution to a prior state. This is an active state-change operation that affects program execution flow, not merely reading data. While it uses a previously saved snapshot (making it somewhat reversible), it triggers an external operation that alters the current execution context — classifying it as Execute.

From the tool's definition Restore a previously created checkpoint, instantly

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

checkpoint_restore Rate-limited

checkpoint_restore 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": {
    "checkpoint_restore": {
      "limits": [
        {
          "counter": "checkpoint_restore_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 Rr, so you can run agents against it safely.

FAQ

Questions about checkpoint_restore

What does the checkpoint_restore tool do? +

Restore a previously created checkpoint, instantly. It is categorised as a Execute tool in the Rr MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on checkpoint_restore? +

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

What risk level is checkpoint_restore? +

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

Can I rate-limit checkpoint_restore? +

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

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

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