gemini_run_code_tool · MCP Gemini MCP: Risk & Policy

WHAT IT DOES

What gemini_run_code_tool does on MCP Gemini

AI agents invoke gemini_run_code_tool to trigger actions in MCP Gemini. 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_run_code_tool needs a policy

This tool runs arbitrary code, which is a classic Execute category action. Code execution can have broad side effects depending on the code submitted—it could read files, modify systems, trigger network requests, or interact with external services. While the tool itself does not inherently delete data or move money, unrestricted code execution poses significant risk of unintended consequences.

From the tool's definition Tool name contains 'run_code_tool' and description states 'Execute code using Gemini's built-in code execution.' The word 'Execute' directly indicates code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_run_code_tool Rate-limited

gemini_run_code_tool 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_run_code_tool": {
      "limits": [
        {
          "counter": "gemini_run_code_tool_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 MCP Gemini, so you can run agents against it safely.

FAQ

Questions about gemini_run_code_tool

What does the gemini_run_code_tool tool do? +

Execute code using Gemini's built-in code execution. It is categorised as a Execute tool in the MCP Gemini 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_run_code_tool? +

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

What risk level is gemini_run_code_tool? +

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

Can I rate-limit gemini_run_code_tool? +

Yes. Add a rate_limit block to the gemini_run_code_tool 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_run_code_tool completely? +

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

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