ChatGPT Workspace Agents

OpenAI's configurable agents inside a ChatGPT workspace. A workspace agent is built and published within the workspace, is gated by workspace role-based access control, and can be given access to apps/MCP server integrations as tools. OpenAI documents a Workspace Agents API scope and a published API trigger channel for triggering runs from external systems.

AI capabilities recorded

• App and MCP server actions

  Active · verified 2026-09-22

  ChatGPT Workspace Agents using configured apps / MCP server integrations as tools: retrieving and searching information in connected external systems and, where the integration supports it and the configured policy permits it, performing actions that change state in those systems. OpenAI's current documentation treats "app" and "MCP server" as the same connected integration. Effective access is layered: an agent instruction alone grants nothing, and a request must pass workspace/Workspace-Agents access, plugin and app availability, a configured connection, the connection's authenticated identity, the connected service's own scopes, Action control (which actions are permitted) and App permissions (when human confirmation is required). This record covers that tool-action surface only; scheduled runs and API-triggered runs are separate initiation mechanisms and are excluded. OpenAI applies no preview, beta or general-availability label to this surface in the accessible primary material, and none is inferred here.