call_gemini_non_stream_thinking · Gemini MCP Server MCP

WHAT IT DOES

What call_gemini_non_stream_thinking does on Gemini MCP Server

AI agents invoke call_gemini_non_stream_thinking to trigger actions in Gemini 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 call_gemini_non_stream_thinking needs a policy

This tool triggers an external API call to Gemini AI models, executing a request and returning a response. It involves invoking an external service whose effects depend on the arguments passed (e.g., the prompt/content sent). This qualifies as Execute since it runs an external operation with argument-dependent behavior.

From the tool's definition Call Gemini API - Non-stream thinking mode

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_gemini_non_stream_thinking Rate-limited

call_gemini_non_stream_thinking 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": {
    "call_gemini_non_stream_thinking": {
      "limits": [
        {
          "counter": "call_gemini_non_stream_thinking_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about call_gemini_non_stream_thinking

What does the call_gemini_non_stream_thinking tool do? +

Call Gemini API - Non-stream thinking mode. It is categorised as a Execute tool in the Gemini 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 call_gemini_non_stream_thinking? +

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

What risk level is call_gemini_non_stream_thinking? +

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

Can I rate-limit call_gemini_non_stream_thinking? +

Yes. Add a rate_limit block to the call_gemini_non_stream_thinking 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 call_gemini_non_stream_thinking completely? +

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

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