Official Technical Resources: OpenAI (page 14)
Official Technical Resources · OpenAI: 258 entries in total; this page lists entries 196–210.
Remote MCP server review requirements
Prepare a plugin's remote MCP server and optional UI for public review.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Local services Get Quote conversion spec
Contract for integrating a local services quote-request plugin into ChatGPT's conversion flow.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Product checkout conversion spec
Contract for integrating a product checkout plugin into ChatGPT's conversion flow.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Restaurant reservation conversion spec
Contract for integrating a restaurant reservation plugin into ChatGPT's Reserve flow.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Security & Privacy
Security and privacy considerations for plugins.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · Agent Identity, Authorization, and Secrets
Link last checked: 2026-09-24
Define tools
Translate plugin use cases into a focused MCP tool surface.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Model Context Protocol (MCP) · Tool Calling
Link last checked: 2026-09-24
Authenticate with Workspace Agent access tokens
Provision and use bearer credentials for the Workspace Agents API.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Guardrails · Agent Identity, Authorization, and Secrets
Link last checked: 2026-09-24
Trigger workspace agent runs
Kick off ChatGPT workspace agents from server-side systems or automations.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: Workflow Orchestration · Model Deployment Options
Link last checked: 2026-09-24
Agentic commerce in production
Checklist for launching in production and FAQs
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Best practices
Operational guidance for high-quality integrations.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Key concepts
Understand the concepts of the Agentic Commerce Protocol
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Agentic Checkout Spec
Merchants integrate with OpenAI’s checkout flow by implementing the Agentic Checkout Spec
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Delegated Payment Spec
Payment Service Providers implement the Delegated Payment Spec to handle and secure Agentic Commerce transactions
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Products
Submit product data for discovery in ChatGPT, with separate requirements for Ads and checkout.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Agent · Model Deployment Options
Link last checked: 2026-09-24
Codex as a platform: build on the open agent harness
Build Codex into the products and workflows your users already know.
Evidence use: For understanding, implementation, selection, reliability, security or migration decisions.
Limitations: Directly evidences only OpenAI's own implementation and claims. Recheck the page status and version before use.
Related concepts: AI Coding Tools · Code Generation / AI Coding
Link last checked: 2026-09-24