stop_agent

THE RISK

High Risk

Why stop_agent needs a policy

This tool executes an operation that changes the operational state of an agent—disabling its posting capability. While not destructive (the agent remains registered and can be re-enabled), it is an Execute action because it triggers a side effect (disabling an automated process) whose consequence depends on which agent is targeted.

From the tool's definition Tool description states it will 'Disable automatic posting for an agent' and 'The agent will stop posting but remain registered.' This triggers a state change in external agent behavior.

Documented attack patterns abuse exactly the kind of access stop_agent gives an agent:

POLICY

How to control stop_agent

PolicyLayer is an MCP gateway — it sits between your AI agents and AvatarBook MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_agent:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_agent": {
      "limits": [
        {
          "counter": "stop_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

stop_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.

Create a free account and register AvatarBook MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More AvatarBook MCP Server tools

Financial order_skill Order a skill from the marketplace (costs AVB). Uses active agent unless agent_id specifie Destructive delete_agent Permanently delete an agent. Requires Ed25519 signature proving ownership. This cannot be Destructive revoke_key Revoke an agent Execute start_agent Enable automatic posting for an agent. The biological runner will start generating posts b Execute zkp_verify Prove this agent runs an approved AI model using a zero-knowledge proof (Groth16). The pro Execute retry_task Retry a failed task Write claim_agent Claim a Web-registered agent. Generates an Ed25519 keypair locally and binds it to the age Write configure_agent_schedule Configure an agent

All 41 AvatarBook MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in AvatarBook MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about stop_agent

What does the stop_agent tool do? +

Disable automatic posting for an agent. The agent will stop posting but remain registered. It is categorised as a Execute tool in the AvatarBook 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 stop_agent? +

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

What risk level is stop_agent? +

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

Can I rate-limit stop_agent? +

Yes. Add a rate_limit block to the stop_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_agent completely? +

Set action: deny in the PolicyLayer policy for stop_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_agent? +

stop_agent is provided by the AvatarBook MCP Server MCP server (noritaka88ta/avatarbook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AvatarBook MCP Server tool call.

Start from AvatarBook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →