ask_agent

SERVERGrabblist SOURCEhttps://mcp.grabbitapp.com/api/mcp

Low RISK CLASS

Category Read

Parameters 21 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-grabbitapp-grabblist/ask-agent.md

WHAT IT DOES

What ask_agent does on Grabblist

AI agents call ask_agent to retrieve information from Grabblist without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`model`	string	—	AI model to use (default: sonnet). haiku=fast/cheap, sonnet=balanced, opus=most capable
`message`	string	Yes	The question or task for the Grabblist assistant

Parameters from the server's own tool schema.

RISK

Why ask_agent is rated Low

Even though ask_agent only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ask_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Grabblist, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ask_agent, this is the rule to start with:

ask_agent Allowed

ask_agent is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ask_agent": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Grabblist, apply this rule, and every ask_agent call is checked against it from then on.

FAQ

Questions about ask_agent

What does the ask_agent tool do? +

Delegate a task to Grabblist's built-in AI assistant. The agent knows the user's Grabblist and can answer questions, compare items, give shopping advice, or analyze saved products. Use this when you want a second opinion or a specialized shopping assistant perspective. Requires the user to have an Anthropic API key configured in Settings. It is categorised as a Read tool in the Grabblist MCP Server, which means it retrieves data without modifying state.

What parameters does ask_agent accept? +

ask_agent accepts 2 parameters: model, message. Required: message. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on ask_agent? +

Register the Grabblist MCP server in PolicyLayer and add a rule for ask_agent: 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 Grabblist. Nothing to install.

What risk level is ask_agent? +

ask_agent is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ask_agent? +

Yes. Add a rate_limit block to the ask_agent 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.

How do I block ask_agent completely? +

Set action: deny in the PolicyLayer policy for ask_agent. 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.

What MCP server provides ask_agent? +

ask_agent is provided by the Grabblist MCP server (https://mcp.grabbitapp.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Grabblist, and thousands of servers like it.

This server

All 23 Grabblist tools →

Across the catalogue

ask_about_cocktail on Cocktails RAG MCP Server →ask_codebase on ACE-MCP → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →