stop_contemplation · MCP Contemplation MCP: Risk & Policy

WHAT IT DOES

What stop_contemplation does on MCP Contemplation

AI agents invoke stop_contemplation to trigger actions in MCP Contemplation. 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_contemplation needs a policy

This tool executes a command that fundamentally alters the state of the MCP server's contemplation system. Stopping an active background cognitive process is an Execute action because it triggers an operation whose effects are immediate and observable (the contemplation loop ceases).

From the tool's definition The tool 'stop_contemplation' performs an action that triggers the stopping of an active background process ('Stop the contemplation loop'). This is an execution of a command with external state effects—terminating a running operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_contemplation Rate-limited

stop_contemplation 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_contemplation": {
      "limits": [
        {
          "counter": "stop_contemplation_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 MCP Contemplation, so you can run agents against it safely.

FAQ

Questions about stop_contemplation

What does the stop_contemplation tool do? +

Stop the contemplation loop. It is categorised as a Execute tool in the MCP Contemplation 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_contemplation? +

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

What risk level is stop_contemplation? +

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

Can I rate-limit stop_contemplation? +

Yes. Add a rate_limit block to the stop_contemplation 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_contemplation completely? +

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

stop_contemplation is provided by the MCP Contemplation MCP server (mikeybeez/mcp-contemplation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.