AI agents invoke ask to trigger actions in MCP Server with Google ADK. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool acts as an orchestrator that dispatches to other agents including code generation and data analysis. Since it can trigger any of the sibling tools (including generate_code and analyze_data), its blast radius is governed by the most severe action it could route to. Code generation and execution via an LLM-based router represents an Execute-level risk.
From the tool's definition 'Routes the user' — description is truncated/uninformative, but the server description states an 'LLM-based router' that coordinates 'multiple specialized agents (search, data analysis, code generation)'. The 'ask' tool routes requests to these agents.
Documented attack patterns abuse exactly the kind of access ask gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server with Google ADK, and nothing reaches the server without passing your rules. This is the rule we recommend for ask:
{
"version": "1",
"default": "deny",
"tools": {
"ask": {
"limits": [
{
"counter": "ask_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ask stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Routes the user. It is categorised as a Execute tool in the MCP Server with Google ADK MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Server with Google ADK MCP server in PolicyLayer and add a rule for ask: 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 Server with Google ADK. Nothing to install.
ask is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ask 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. 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 is provided by the MCP Server with Google ADK MCP server (zayedrais/ai_agent_with_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server with Google ADK, 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.
4 MCP Server with Google ADK tools catalogued and risk-classified — across an index of 43,000+ MCP servers.