gemini_prompt_structured · Geminicli MCP: Risk & Policy

WHAT IT DOES

What gemini_prompt_structured does on Geminicli

AI agents invoke gemini_prompt_structured to trigger actions in Geminicli. 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_prompt_structured needs a policy

This tool executes code/commands by invoking the Gemini CLI and making API calls to Google's models. While the immediate effect is text generation, the tool's capability to execute arbitrary prompts and invoke external services qualifies it as Execute rather than Read.

From the tool's definition Tool description states it 'Invoke[s] the headless Gemini CLI' and processes responses, indicating execution of external operations. The tool sends prompts to Google's Gemini models, which are remote API calls with effects determined by the prompt argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_prompt_structured Rate-limited

gemini_prompt_structured 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_prompt_structured": {
      "limits": [
        {
          "counter": "gemini_prompt_structured_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 Geminicli, so you can run agents against it safely.

FAQ

Questions about gemini_prompt_structured

What does the gemini_prompt_structured tool do? +

Invoke the headless Gemini CLI and parse its response as JSON validated against a caller-provided JSON Schema. Stateless. Fails loudly with an isError result if the response is not valid JSON or does not match the schema. It is categorised as a Execute tool in the Geminicli 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_prompt_structured? +

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

What risk level is gemini_prompt_structured? +

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

Can I rate-limit gemini_prompt_structured? +

Yes. Add a rate_limit block to the gemini_prompt_structured 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_prompt_structured completely? +

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

gemini_prompt_structured is provided by the Geminicli MCP server (trevoraspencer/geminicli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.