Ask user for advice when agent encounters uncertainty, problems, or needs guidance. Use this when you
AI agents call ask_user_advice to retrieve information from Agent Knowledge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the user for information/guidance in response to agent uncertainty or problems. It is purely informational (Read category) with no capability to modify, delete, execute external operations, or commit financial actions. The severity is low because the tool merely facilitates communication and does not alter any underlying data structures or trigger irreversible operations.
From the tool's definition Tool description indicates it 'Ask[s] user for advice' - a retrieval of user input/guidance with no side effects on data or systems.
Documented attack patterns abuse exactly the kind of access ask_user_advice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Knowledge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for ask_user_advice:
{
"version": "1",
"default": "deny",
"tools": {
"ask_user_advice": {}
}
}ask_user_advice 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.
Ask user for advice when agent encounters uncertainty, problems, or needs guidance. Use this when you. It is categorised as a Read tool in the Agent Knowledge MCP MCP Server, which means it retrieves data without modifying state.
Register the Agent Knowledge MCP server in PolicyLayer and add a rule for ask_user_advice: 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 Agent Knowledge MCP. Nothing to install.
ask_user_advice 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_advice 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_advice. 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_advice is provided by the Agent Knowledge MCP server (itshare4u/agentknowledgemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Knowledge MCP, 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.
27 Agent Knowledge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.