Ask user to confirm an action before proceeding with potentially impactful operations
AI agents call confirm_action 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 retrieves user intent/consent via confirmation dialog. It has no autonomous execution capability, does not modify data, and does not perform irreversible actions. The actual execution of potentially impactful operations happens elsewhere (outside this tool). This tool is purely a Read operation that gathers user input to inform downstream decisions.
From the tool's definition Tool asks user to confirm an action through a prompt/question mechanism. The description states it 'Ask[s] user to confirm' - a query operation seeking user input, with no capability to execute, modify, or delete data.
Attacks that exploit this kind of access
Ask user to confirm an action before proceeding with potentially impactful operations. 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 confirm_action: 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.
confirm_action 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 confirm_action 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 confirm_action. 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.
confirm_action 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 →