stop_conscious_agent · Session Buddy MCP: Risk & Policy

WHAT IT DOES

What stop_conscious_agent does on Session Buddy

AI agents invoke stop_conscious_agent to trigger actions in Session Buddy. 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 stop_conscious_agent needs a policy

The tool performs an active operation that stops a running agent or process. This is an Execute-class action because it runs/triggers an operation whose effect depends on the system state (whether the agent is running). It is not Read (no data retrieval), not Write (not creating/modifying reversible data), not Destructive (stopping a service is typically reversible via restart), and not Financial.

From the tool's definition Tool description states 'Stop background Conscious Agent if running' — this is an action that terminates a running process/agent, which is an execution operation that triggers an external effect (stopping a background service).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_conscious_agent Rate-limited

stop_conscious_agent 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": {
    "stop_conscious_agent": {
      "limits": [
        {
          "counter": "stop_conscious_agent_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 Session Buddy, so you can run agents against it safely.

FAQ

Questions about stop_conscious_agent

What does the stop_conscious_agent tool do? +

Stop background Conscious Agent if running. It is categorised as a Execute tool in the Session Buddy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_conscious_agent? +

Register the Session Buddy MCP server in PolicyLayer and add a rule for stop_conscious_agent: 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 Session Buddy. Nothing to install.

What risk level is stop_conscious_agent? +

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

Can I rate-limit stop_conscious_agent? +

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

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

stop_conscious_agent is provided by the Session Buddy MCP server (lesleslie/session-buddy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.