query_gemini · Gemini MCP Server for Claude Code MCP

WHAT IT DOES

What query_gemini does on Gemini MCP Server for Claude Code

AI agents invoke query_gemini to trigger actions in Gemini MCP Server for Claude Code. 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_gemini needs a policy

This tool sends queries to an external AI service (Google Gemini), constituting an external operation. It is not a simple local read — it invokes a third-party API, consumes tokens, and may trigger multi-turn conversations. The description is very sparse ('Query Google'), but context from the server description clarifies it queries Gemini AI models for responses, code comparisons, etc.

From the tool's definition Tool name 'query_gemini' and description 'Query Google' — triggers an external operation (API call to Google's Gemini AI models) whose effects depend on arguments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_gemini Rate-limited

query_gemini 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_gemini": {
      "limits": [
        {
          "counter": "query_gemini_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 Gemini MCP Server for Claude Code, so you can run agents against it safely.

FAQ

Questions about query_gemini

What does the query_gemini tool do? +

Query Google. It is categorised as a Execute tool in the Gemini MCP Server for Claude Code 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_gemini? +

Register the Gemini MCP Server for Claude Code MCP server in PolicyLayer and add a rule for query_gemini: 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 Gemini MCP Server for Claude Code. Nothing to install.

What risk level is query_gemini? +

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

Can I rate-limit query_gemini? +

Yes. Add a rate_limit block to the query_gemini 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_gemini completely? +

Set action: deny in the PolicyLayer policy for query_gemini. 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_gemini? +

query_gemini is provided by the Gemini MCP Server for Claude Code MCP server (raydollete/gemini-for-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.