OpenAI · AI
OPENAI_CHAT_COMPLETION
Call OpenAI chat completions using the user's connected OpenAI key. Returns { message, usage }.
- Provider
- OpenAI
- Access
- Read
- Category
- AI
- Version
- v1
Input schema
{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Model id, e.g. gpt-4o."
},
"messages": {
"type": "array",
"description": "OpenAI chat messages array."
}
},
"required": [
"model",
"messages"
],
"additionalProperties": false
}How to call it
Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls openai_chat_completion with arguments matching the schema above.
CybrLink validates the input, injects the connected OpenAI credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.
Frequently asked
- How do I let an AI agent openai chat completion?
- Connect OpenAI to CybrLink, then expose the `openai_chat_completion` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the OpenAI credential server-side and runs one scoped API call. Call OpenAI chat completions using the user's connected OpenAI key. Returns { message, usage }.
- Does the AI model see my OpenAI credentials when using OPENAI_CHAT_COMPLETION?
- No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can read this data from OpenAI without the OAuth token or API key ever entering its context.