query_ai_agent · MelviChat MCP Server MCP: Risk & Policy

WHAT IT DOES

What query_ai_agent does on MelviChat MCP Server

AI agents invoke query_ai_agent to trigger actions in MelviChat MCP Server. 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.

WHY IT NEEDS A POLICY

Why query_ai_agent needs a policy

This tool invokes an external AI agent (Google Gemini) to query/reason about the main database. While 'consultar' (query/consult) suggests a read-like intent, executing an AI agent against a live database introduces unpredictable side effects depending on what the agent does, and it operates on the main/principal database.

From the tool's definition 'Consultar al Agente IA del sistema (Gemini) sobre la base de datos principal' — triggers an external AI agent (Gemini) operation against the main database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_ai_agent Rate-limited

query_ai_agent 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_ai_agent": {
      "limits": [
        {
          "counter": "query_ai_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MelviChat MCP Server, so you can run agents against it safely.

FAQ

Questions about query_ai_agent

What does the query_ai_agent tool do? +

Consultar al Agente IA del sistema (Gemini) sobre la base de datos principal. It is categorised as a Execute tool in the MelviChat MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_ai_agent? +

Register the MelviChat MCP Server MCP server in PolicyLayer and add a rule for query_ai_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 MelviChat MCP Server. Nothing to install.

What risk level is query_ai_agent? +

query_ai_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_ai_agent? +

Yes. Add a rate_limit block to the query_ai_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 query_ai_agent completely? +

Set action: deny in the PolicyLayer policy for query_ai_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 query_ai_agent? +

query_ai_agent is provided by the MelviChat MCP Server MCP server (melvi24/mcp-chat-ia). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.