MCP Server Policy

OPENAI MCP POLICY

Enforce policies on every tool call to the OpenAI MCP Server. 1 tools listed, categorised, and ready for rules.

openai-mcp-server 0 read 1 write 1 tools total

openai ai language-model chat

GET STARTED

Download this policy scaffold and add your rules. Intercept enforces them on every tool call before it reaches OpenAI.

terminal

# Download policy scaffold


curl -o openai.yaml https://raw.githubusercontent.com/policylayer/intercept/main/policies/openai.yaml

# Run with Intercept


intercept --policy openai.yaml -- npx -y @openai-mcp-server

Server documentation: https://www.npmjs.com/package/openai-mcp-server

OTHER TOOLS

openai_chat Send a prompt to OpenAI and receive a response

POLICY YAML

This scaffold lists every tool with empty rules. Add conditions — rate limits, argument validation, deny rules — then deploy with Intercept.

openai.yaml

version: "1"
description: "Policy for openai-mcp-server"
default: "allow"
tools:
    openai_chat:
        rules: []

RELATED POLICIES

Google Workspace Chat (gws CLI) 37 tools

FREQUENTLY ASKED QUESTIONS

What tools does the OpenAI MCP server expose?

The OpenAI MCP Server exposes 1 tools across 1 categories: Other. Each tool can be individually controlled with Intercept policies.

How do I enforce policies on OpenAI?

Download the policy scaffold, add rules (rate limits, argument validation, deny rules), then run Intercept as a proxy in front of the OpenAI MCP server. Every tool call is evaluated against your YAML policy before execution.

Is the OpenAI policy free to use?

Yes. All Intercept policies are open source under the Apache 2.0 licence. Download, modify, and deploy without restrictions.

ENFORCE POLICIES ON OPENAI

Open source. One binary. Zero dependencies.

VIEW ON GITHUB Browse all policies →