gemini_json · Gemini CLI MCP Server MCP: Risk & Policy

WHAT IT DOES

What gemini_json does on Gemini CLI MCP Server

AI agents invoke gemini_json 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_json needs a policy

Based on the server context, this tool likely executes Gemini CLI prompts with JSON-formatted output. Sibling tools like 'run_gemini' and 'gemini_with_context' suggest execution of AI prompts. Empty description lowers confidence significantly. Categorized as Execute due to the pattern of CLI execution tools on this server, with high severity given potential for arbitrary prompt execution.

From the tool's definition Tool name 'gemini_json' on a server described as wrapping Gemini CLI to execute prompts; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_json Rate-limited

gemini_json 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_json": {
      "limits": [
        {
          "counter": "gemini_json_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_json

What does the gemini_json tool do? +

gemini_json. 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_json? +

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

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

Can I rate-limit gemini_json? +

Yes. Add a rate_limit block to the gemini_json 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_json completely? +

Set action: deny in the PolicyLayer policy for gemini_json. 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_json? +

gemini_json 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.