run_gemini · Gemini CLI MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_gemini does on Gemini CLI MCP Server

AI agents invoke run_gemini to trigger actions in Gemini CLI 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 run_gemini needs a policy

Although the tool description is empty, the context strongly indicates this tool executes Gemini CLI prompts/commands. Execution tools pose high risk because their effects depend entirely on the prompt content supplied by an AI agent—the agent could invoke the Gemini CLI to perform arbitrary operations including data retrieval, modification, or damage depending on what the CLI supports.

From the tool's definition Tool name 'run_gemini' paired with sibling tools 'gemini_shell' and 'gemini_json' indicates this executes Gemini CLI commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_gemini Rate-limited

run_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": {
    "run_gemini": {
      "limits": [
        {
          "counter": "run_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 CLI MCP Server, so you can run agents against it safely.

FAQ

Questions about run_gemini

What does the run_gemini tool do? +

run_gemini. It is categorised as a Execute tool in the Gemini CLI 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 run_gemini? +

Register the Gemini CLI MCP Server MCP server in PolicyLayer and add a rule for run_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 CLI MCP Server. Nothing to install.

What risk level is run_gemini? +

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

Can I rate-limit run_gemini? +

Yes. Add a rate_limit block to the run_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 run_gemini completely? +

Set action: deny in the PolicyLayer policy for run_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 run_gemini? +

run_gemini is provided by the Gemini CLI MCP Server MCP server (wminson/gemini_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.