Ask a yes/no confirmation question to the user when the AI needs clarification or verification
AI agents call ask_yes_no to retrieve information from MCP-Confirm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is purely informational—it queries the user for a yes/no response to clarify or verify something, then returns their answer. It has no side effects on data, systems, or state. It is a read operation in the sense that it retrieves user input without modifying anything irreversibly or executing external commands.
From the tool's definition Tool name 'ask_yes_no' and description 'Ask a yes/no confirmation question to the user when the AI needs clarification or verification' indicates the tool retrieves user input/feedback through a question prompt.
Attacks that exploit this kind of access
Ask a yes/no confirmation question to the user when the AI needs clarification or verification. It is categorised as a Read tool in the MCP-Confirm MCP Server, which means it retrieves data without modifying state.
Register the MCP-Confirm MCP server in PolicyLayer and add a rule for ask_yes_no: 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 MCP-Confirm. Nothing to install.
ask_yes_no 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_yes_no 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_yes_no. 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_yes_no is provided by the MCP-Confirm MCP server (mako10k/mcp-confirm). 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 →