Critical Risk →

agent_uninstall

Remove a locally installed ACP agent.

Part of the Mcacp server.

agent_uninstall can permanently delete data in Mcacp, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE MCACP →

Free to start. No card required.

AI agents may call agent_uninstall to permanently remove or destroy resources in Mcacp. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call agent_uninstall in a loop, permanently destroying resources in Mcacp. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "agent_uninstall"
  ]
}

See the full Mcacp policy for all 24 tools.

Get this rule live on your own Mcacp server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY MCACP →

View all 24 tools →

These attack patterns abuse exactly the kind of access agent_uninstall gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so agent_uninstall only ever does what you allow.

SECURE MCACP →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the agent_uninstall tool do? +

Remove a locally installed ACP agent.. It is categorised as a Destructive tool in the Mcacp 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 agent_uninstall? +

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

What risk level is agent_uninstall? +

agent_uninstall 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 agent_uninstall? +

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

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

agent_uninstall is provided by the Mcacp MCP server (mcacp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcacp tool call.

Deterministic rules across all 24 Mcacp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.