Ask the user for a single binary decision with positive/negative outcome. ONLY USE FOR: Single actions that can be confirmed or declined (e.g.,
AI agents call ask_user_confirm to retrieve information from Interactive MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool passively retrieves user input (a confirmation choice) without side effects. It is a human-in-the-loop interaction mechanism that elicits a binary response. The actual action being confirmed is performed by separate logic, not by this tool itself. This fits the Read category: retrieves user intent/choice with no autonomous side effects.
From the tool's definition Tool requests user input through an interactive popup with a binary decision (confirm/decline). The description states it is 'ONLY USE FOR: Single actions that can be confirmed or declined', indicating it prompts for confirmation without executing actions…
Attacks that exploit this kind of access
Ask the user for a single binary decision with positive/negative outcome. ONLY USE FOR: Single actions that can be confirmed or declined (e.g.,. It is categorised as a Read tool in the Interactive MCP MCP Server, which means it retrieves data without modifying state.
Register the Interactive MCP server in PolicyLayer and add a rule for ask_user_confirm: 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 Interactive MCP. Nothing to install.
ask_user_confirm is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ask_user_confirm 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.
Set action: deny in the PolicyLayer policy for ask_user_confirm. 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.
ask_user_confirm is provided by the Interactive MCP server (raz-labs/interactive-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →