Request user confirmation before proceeding
AI agents call confirm_action to retrieve information from MCP TypeScript Starter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a utility tool that prompts for human approval. The confirmation flow itself is a read operation—it queries user consent without side effects. While downstream actions may have consequences, this tool itself only performs information gathering. No blast radius from misuse of the tool itself, as it merely requests human input.
From the tool's definition Tool name 'confirm_action' and description 'Request user confirmation before proceeding' indicate this tool reads/queries user intent. It retrieves confirmation status but does not modify data, execute external commands, or perform destructive operations.
Documented attack patterns abuse exactly the kind of access confirm_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP TypeScript Starter, and nothing reaches the server without passing your rules. This is the rule we recommend for confirm_action:
{
"version": "1",
"default": "deny",
"tools": {
"confirm_action": {}
}
}confirm_action is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Request user confirmation before proceeding. It is categorised as a Read tool in the MCP TypeScript Starter MCP Server, which means it retrieves data without modifying state.
Register the MCP TypeScript Starter 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 TypeScript Starter. 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 TypeScript Starter MCP server (sammorrowdrums/mcp-typescript-starter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP TypeScript Starter, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 MCP TypeScript Starter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.