Create a custom confirmation dialog with specific schema when standard tools don
AI agents call elicit_custom 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 creates a custom confirmation/dialog prompt to collect user input, similar to the other confirmation tools on this server (ask_yes_no, clarify_intent, collect_rating). It reads/retrieves user input rather than writing, executing, or destroying data. The truncated description reduces confidence, but given the server's purpose of AI-user confirmation protocols, this is almost certainly a UI prompt tool.
From the tool's definition 'Create a custom confirmation dialog' — presents a dialog to the user to elicit a response; 'when standard tools don' (description appears truncated)
Attacks that exploit this kind of access
Create a custom confirmation dialog with specific schema when standard tools don. 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 elicit_custom: 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.
elicit_custom 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 elicit_custom 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 elicit_custom. 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.
elicit_custom 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 →