gemini_prompt_with_context · Geminicli MCP: Risk & Policy

WHAT IT DOES

What gemini_prompt_with_context does on Geminicli

AI agents invoke gemini_prompt_with_context 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_with_context needs a policy

This tool executes external operations (invoking Gemini CLI and sending queries to Google's Gemini models) based on user-supplied arguments. While the immediate output is text and appears read-only on its surface, it is fundamentally an Execute action because: (1) it invokes an external service whose behavior depends entirely on the prompt content, (2) the context parameter allows injection of arbitrary information…

From the tool's definition Tool invokes the headless Gemini CLI with a prompt plus context, runs in the MCP server — this is a code/command execution interface that triggers an external operation (Gemini API call) whose effects depend on the prompt and context arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_prompt_with_context Rate-limited

gemini_prompt_with_context 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_with_context": {
      "limits": [
        {
          "counter": "gemini_prompt_with_context_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_with_context

What does the gemini_prompt_with_context tool do? +

Invoke the headless Gemini CLI with a prompt plus a separate context block. Stateless — each call is an independent turn. The context is prepended to the prompt inside a <context> tag. Runs in the MCP server. 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_with_context? +

Register the Geminicli MCP server in PolicyLayer and add a rule for gemini_prompt_with_context: 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_with_context? +

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

Can I rate-limit gemini_prompt_with_context? +

Yes. Add a rate_limit block to the gemini_prompt_with_context 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_with_context completely? +

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

gemini_prompt_with_context 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.