Critical Risk →

acknowledge_signal

Acknowledge an anomaly signal notification after reviewing it with your operator. Records that the notification has been reviewed. Acknowledgements expire after 30 days. Does not remove the observation from the network — only records that you have reviewed the signal.

Part of the ACR — Agent Composition Records MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

@tethral/acr-mcp Destructive

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

Without a policy, an AI agent could call acknowledge_signal in a loop, permanently destroying resources in ACR — Agent Composition Records. There is no undo for destructive operations. Intercept 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.

acr-agent-composition-records.yaml
tools:
  acknowledge_signal:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full ACR — Agent Composition Records policy for all 30 tools.

Tool Name acknowledge_signal
Category Destructive
Risk Level Critical

View all 30 tools →

Agents calling destructive-class tools like acknowledge_signal have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

acknowledge_signal is one of the critical-risk operations in ACR — Agent Composition Records. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

What does the acknowledge_signal tool do? +

Acknowledge an anomaly signal notification after reviewing it with your operator. Records that the notification has been reviewed. Acknowledgements expire after 30 days. Does not remove the observation from the network — only records that you have reviewed the signal.. It is categorised as a Destructive tool in the ACR — Agent Composition Records 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 acknowledge_signal? +

Add a rule in your Intercept YAML policy under the tools section for acknowledge_signal. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the ACR — Agent Composition Records MCP server.

What risk level is acknowledge_signal? +

acknowledge_signal 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 acknowledge_signal? +

Yes. Add a rate_limit block to the acknowledge_signal rule in your Intercept 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 acknowledge_signal completely? +

Set action: deny in the Intercept policy for acknowledge_signal. 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 acknowledge_signal? +

acknowledge_signal is provided by the ACR — Agent Composition Records MCP server (@tethral/acr-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.