session_close · Rr MCP: Risk & Policy

WHAT IT DOES

What session_close does on Rr

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

WHY IT NEEDS A POLICY

Why session_close needs a policy

An AI agent can call session_close faster than any human can review — one bad instruction and it creates or modifies resources in Rr by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_close Rate-limited

session_close 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": {
    "session_close": {
      "limits": [
        {
          "counter": "session_close_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 session_close

What does the session_close tool do? +

End a replay session and clean up its GDB/rr process. It is categorised as a Write tool in the Rr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on session_close? +

Register the Rr MCP server in PolicyLayer and add a rule for session_close: 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 session_close? +

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

Can I rate-limit session_close? +

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

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

session_close 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.