MCP Tool Reference Low Risk

openai_chat

Send a prompt to OpenAI and receive a response

Part of the OpenAI MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

openai-mcp-server Other

WHEN AI AGENTS USE THIS TOOL

AI agents call openai_chat to perform operations in OpenAI. While the risk category is not fully classified, applying a rate limit gives you visibility into how often the tool is called and prevents unexpected bursts of activity from autonomous agents.

WHY ENFORCE A POLICY ON OPENAI_CHAT

Applying a policy to openai_chat gives you an audit trail of every call an AI agent makes. Even for low-risk tools, visibility into agent behaviour helps you debug issues, optimise workflows, and maintain compliance with your organisation's security requirements.

RECOMMENDED POLICY

Apply a rate limit to control usage and monitor for unexpected behaviour.

openai.yaml 
tools:
  openai_chat:
    rules:
      - action: allow
        rate_limit:
          max: 60
          window: 60

See the full OpenAI policy for all 1 tools.

DETAILS

Tool Name

openai_chat

Category

Other

MCP Server

OpenAI MCP Server

Risk Level

Low

SIMILAR OTHER TOOLS ON OTHER SERVERS

analytics Algolia
Access Algolia analytics data
monitoring Algolia
Monitor Algolia service status
recommend Algolia
Access Algolia recommendation features
abtesting Algolia
Manage A/B tests
collections Algolia
Manage query suggestions collections
usage Algolia
Access Algolia usage data

RELATED READING

FREQUENTLY ASKED QUESTIONS

What does the openai_chat tool do?

Send a prompt to OpenAI and receive a response. It is categorised as a Other tool in the OpenAI MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on openai_chat?

Add a rule in your Intercept YAML policy under the tools section for openai_chat. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the OpenAI MCP server.

What risk level is openai_chat?

openai_chat is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit openai_chat?

Yes. Add a rate_limit block to the openai_chat rule in your Intercept 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_chat completely?

Set action: deny in the Intercept policy for openai_chat. 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_chat?

openai_chat is provided by the OpenAI MCP server (openai-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

ENFORCE POLICIES ON OPENAI

Open source. One binary. Zero dependencies.

VIEW ON GITHUB Full OpenAI policy →