openai_query · Geoseo MCP: Risk & Policy

WHAT IT DOES

What openai_query does on Geoseo

AI agents invoke openai_query to trigger actions in Geoseo. 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 openai_query needs a policy

This tool triggers an external operation — querying the OpenAI ChatGPT API with web search enabled. It goes beyond a simple read because it causes an external system (ChatGPT) to perform a web search and generate a response, constituting an execution of an external service call with variable effects depending on the query.

From the tool's definition Ask ChatGPT (with web search) a question; return answer + cited URLs

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

openai_query Rate-limited

openai_query 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": {
    "openai_query": {
      "limits": [
        {
          "counter": "openai_query_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 Geoseo, so you can run agents against it safely.

FAQ

Questions about openai_query

What does the openai_query tool do? +

Ask ChatGPT (with web search) a question; return answer + cited URLs. It is categorised as a Execute tool in the Geoseo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on openai_query? +

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

What risk level is openai_query? +

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

Can I rate-limit openai_query? +

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

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

openai_query is provided by the Geoseo MCP server (rachit8484/geoseo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.