Ask the user for free-form text input. BEST FOR: Open-ended questions, detailed explanations, custom input where you need the user to type their own response. Always provide a clear, specific prompt. The prompt supports Markdown formatting (headers, bold, *italic*, lists,
AI agents call ask_user_text 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 is fundamentally a data retrieval mechanism that queries the user for information. It has no side effects on system state, data persistence, or external operations. The input collected is returned to the AI agent for processing but does not cause any irreversible changes, code execution, or financial transactions. It is a read-only interaction pattern analogous to a simple prompt or query.
From the tool's definition Tool description states it 'Ask[s] the user for free-form text input' and is used for 'Open-ended questions, detailed explanations, custom input where you need the user to type their own response.' The tool retrieves user-provided input without modifying,…
Attacks that exploit this kind of access
Ask the user for free-form text input. BEST FOR: Open-ended questions, detailed explanations, custom input where you need the user to type their own response. Always provide a clear, specific prompt. The prompt 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_text: 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_text 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_text 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_text. 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_text 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 →