gemini_shell · Gemini CLI MCP Server MCP: Risk & Policy

WHAT IT DOES

What gemini_shell does on Gemini CLI MCP Server

AI agents invoke gemini_shell 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 gemini_shell needs a policy

This tool allows execution of arbitrary shell commands, which is the highest-impact Execute risk. An AI agent with access to this could run any command on the host system (install malware, exfiltrate data, modify files, pivot to other systems, etc.). The blast radius is system-wide.

From the tool's definition Tool description states 'Execute a shell command through Gemini CLI using ! syntax.' The word 'Execute' combined with 'shell command' clearly indicates arbitrary code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_shell Rate-limited

gemini_shell 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_shell": {
      "limits": [
        {
          "counter": "gemini_shell_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 gemini_shell

What does the gemini_shell tool do? +

Execute a shell command through Gemini CLI using ! syntax. 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 gemini_shell? +

Register the Gemini CLI MCP Server MCP server in PolicyLayer and add a rule for gemini_shell: 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 gemini_shell? +

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

Can I rate-limit gemini_shell? +

Yes. Add a rate_limit block to the gemini_shell 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_shell completely? +

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

gemini_shell 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.

// THE FULL RECORD

gemini_shell is one line of Gemini CLI MCP Server's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →