gemini_query · Gemini Cli MCP: Risk & Policy

WHAT IT DOES

What gemini_query does on Gemini Cli

AI agents invoke gemini_query to trigger actions in Gemini Cli. 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 gemini_query needs a policy

This tool executes queries against an external AI service via CLI, which constitutes triggering external operations. The effects depend entirely on what prompt is passed, and the CLI execution pathway could have side effects beyond simple data retrieval. It is more than a Read because it invokes an external system with arbitrary input.

From the tool's definition "Query Gemini CLI with a prompt" — sends arbitrary prompts to an external AI service (Gemini CLI), triggering external operations whose effects depend on the prompt contents

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_query Rate-limited

gemini_query 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": {
    "gemini_query": {
      "limits": [
        {
          "counter": "gemini_query_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 Cli, so you can run agents against it safely.

FAQ

Questions about gemini_query

What does the gemini_query tool do? +

Query Gemini CLI with a prompt. It is categorised as a Execute tool in the Gemini Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gemini_query? +

Register the Gemini Cli MCP server in PolicyLayer and add a rule for gemini_query: 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 Cli. Nothing to install.

What risk level is gemini_query? +

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

Can I rate-limit gemini_query? +

Yes. Add a rate_limit block to the gemini_query 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 gemini_query completely? +

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

gemini_query is provided by the Gemini Cli MCP server (jwcraig/gemini-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.