Ask the user to choose from multiple predefined options using buttons. BEST FOR: Multiple choice questions, menu selections, preference choices. Each option should be distinct and clear. Users can also provide custom text if none of the buttons fit their needs. The message supports Markdown forma...
AI agents call ask_user_buttons 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 requests information from the user through an interactive dialog and returns their selection. It is fundamentally a retrieval mechanism (user choosing from options) with no capability to modify data, execute commands, delete information, or commit financial obligations. The worst case of misuse is gathering incorrect user input preferences, which is low-impact. Categorized as Read with low severity.
From the tool's definition Tool performs interactive UI prompt that requests user input via buttons with optional custom text fallback. No data creation, modification, deletion, or financial transaction occurs.
Attacks that exploit this kind of access
Ask the user to choose from multiple predefined options using buttons. BEST FOR: Multiple choice questions, menu selections, preference choices. Each option should be distinct and clear. Users can also provide custom text if none of the buttons fit their needs. The message supports Markdown formatting (headers, bold, *italic*, lists,. 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_buttons: 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_buttons 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_buttons 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_buttons. 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_buttons 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 →