> ## Documentation Index > Fetch the complete documentation index at: https://platform.atlan.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write. > The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects. > SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript. > These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces. # Availability and limits > What is on for every organization, what an administrator turns on, and what AI Registry does not do. AI Registry and these docs are in private preview. Behaviour can change between releases, so verify a workflow in your own organization before you rely on it in production. Pages mark what is not on for everyone: * Preview means the product works today but may change. * **Requires enablement** means someone must turn it on before it appears for your organization. ## What is on, and what needs turning on | Product | Status | How to get it | | - | - | - | | [Skill management](/registry/skills/index) and [Agent management](/registry/agents/index) | On for every organization | Nothing to do. | | [Traces](/registry/traces/index) and [FinOps](/finops/index) | On for every organization | Follow [Send and verify traces](/registry/traces/how-tos/send-and-verify). | | [Model Gateway](/gateway/model/index) and [MCP Gateway](/gateway/mcp/index) | On for every organization | Model Gateway serves the models connected for your organization. See [Supported model providers](/gateway/model/references/providers). | | [Evals](/evals/index) | Requires enablement | The eval API is on for every organization. The **Evals** pages in the app are turned on per organization. If you don't see **Evals**, ask your administrator. | | [Metrics Studio](/studios/metrics-studio) | Preview, installed by an administrator | See [Install and manage apps](/registry/apps/how-tos/install-apps). | | [Ontology](/ontology/index) | Preview, installed by an administrator | See [Install and manage apps](/registry/apps/how-tos/install-apps). | | [Billing](/admin/billing/index) | Depends on your plan | If billing is off for your organization, the **Billing** page says so. | To see which apps your organization has, see [Find your installed apps](/registry/apps/how-tos/find-installed-apps). ## Find an enabled app If **Evals** is missing from the app rail, open **⋯** (**More**). Select **Evals**, or pin it to the rail. If there is no **⋯** tile or Evals is not listed, ask your administrator about enablement. The guided **Build an eval** flow has separate enablement. Its absence does not prevent SDK evals or experiment review. ## What AI Registry does not do * **A record does not start an agent.** Registering an agent or recording a session stores what happened. Your framework, runtime, or local coding client runs the agent. See [How agents work](/concepts/how-agents-work). * **An accepted upload is not proof.** A successful trace or session upload does not prove the run completed, or that it landed in the workspace you intended. Confirm it in the app or with a read. See [Send and verify traces](/registry/traces/how-tos/send-and-verify). * **A workspace ID is not access.** What you can see comes from the identity you sign in with and its permissions, not from the ID a caller sends. * **Usage is not a quality verdict.** A high run count shows reuse, not correct results. Use [Evals](/evals/index) to measure quality. * **MCP Gateway does not store tool data.** For calls in a verified session, it can record the tool name, outcome, and duration for audit, but not the arguments or output. Recording is best-effort, and a failed audit write does not stop the tool call. See [Track usage and audit tool calls](/gateway/mcp/how-tos/track-usage-and-audit). * **Metrics Studio and Ontology never run SQL.** They store agreed definitions and context that agents read. Your agent or warehouse runs the query. ## Related * [What is AI Registry](/) * [Platform architecture](/platform/references/architecture) * [Glossary](/concepts/glossary) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.