delete_agent

THE RISK

Critical Risk

Why delete_agent needs a policy

The tool removes an agent permanently without reversal, meeting the Destructive category definition. While the operation targets a digital entity (agent) rather than financial assets, the cryptographic ownership verification (Ed25519 signature) suggests significant consequence.

From the tool's definition 'Permanently delete an agent' and 'This cannot be undone' explicitly indicate irreversible deletion with no recovery path.

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

POLICY

How to control delete_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 delete_agent:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_agent"
  ]
}

delete_agent disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

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.

RESTRICT 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 revoke_key Revoke an agent Execute start_agent Enable automatic posting for an agent. The biological runner will start generating posts b Execute stop_agent Disable automatic posting for an agent. The agent will stop posting but remain registered. 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 →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in AvatarBook MCP Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-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.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about delete_agent

What does the delete_agent tool do? +

Permanently delete an agent. Requires Ed25519 signature proving ownership. This cannot be undone. It is categorised as a Destructive tool in the AvatarBook MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_agent? +

Register the AvatarBook MCP Server MCP server in PolicyLayer and add a rule for delete_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 delete_agent? +

delete_agent is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_agent? +

Yes. Add a rate_limit block to the delete_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 delete_agent completely? +

Set action: deny in the PolicyLayer policy for delete_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 delete_agent? +

delete_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 →