gpt_search · GPT Tools MCP Server MCP: Risk & Policy

WHAT IT DOES

What gpt_search does on GPT Tools MCP Server

AI agents invoke gpt_search to trigger actions in GPT Tools 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 gpt_search needs a policy

The server description explicitly mentions Playwright browser automation to drive external browser actions. A search tool on this server likely triggers browser automation (navigating pages, submitting queries) rather than a simple read-only API call. This constitutes executing external operations. Confidence is reduced because the tool description is empty, leaving the exact behavior uncertain.

From the tool's definition Tool name 'gpt_search' on a server described as using 'Playwright browser automation' to 'delegate web research... to ChatGPT'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gpt_search Rate-limited

gpt_search 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": {
    "gpt_search": {
      "limits": [
        {
          "counter": "gpt_search_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 GPT Tools MCP Server, so you can run agents against it safely.

FAQ

Questions about gpt_search

What does the gpt_search tool do? +

gpt_search. It is categorised as a Execute tool in the GPT Tools 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 gpt_search? +

Register the GPT Tools MCP Server MCP server in PolicyLayer and add a rule for gpt_search: 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 GPT Tools MCP Server. Nothing to install.

What risk level is gpt_search? +

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

Can I rate-limit gpt_search? +

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

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

gpt_search is provided by the GPT Tools MCP Server MCP server (kev489/gpt-tool-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.