Ask structured multiple-choice questions when you have a clear set of options. Use this for preferences, selecting from a list, or simple yes/no/maybe decisions. Choose this over ask-one-question when you can constrain the answer space. Supports single or multiple selection.
AI agents call ask-multiple-choice to retrieve information from AskMeMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (human responses) from a user without side effects. The human makes the choice; the tool merely facilitates the question and collects the answer. It is non-destructive, non-executable, and non-financial. While it depends on human decision-making, the tool itself only performs a read operation by gathering user input.
From the tool's definition Tool requests human input through a web interface for 'preferences, selecting from a list, or simple yes/no/maybe decisions' with 'a clear set of options.' No data creation, modification, deletion, code execution, or financial operations occur.
Attacks that exploit this kind of access
Ask structured multiple-choice questions when you have a clear set of options. Use this for preferences, selecting from a list, or simple yes/no/maybe decisions. Choose this over ask-one-question when you can constrain the answer space. Supports single or multiple selection. It is categorised as a Read tool in the AskMeMCP MCP Server, which means it retrieves data without modifying state.
Register the AskMe MCP server in PolicyLayer and add a rule for ask-multiple-choice: 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 AskMeMCP. Nothing to install.
ask-multiple-choice 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-multiple-choice 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-multiple-choice. 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-multiple-choice is provided by the AskMe MCP server (roman-vm/ask-me-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 →