> For the complete documentation index, see [llms.txt](https://knowledgebase.fabricdata.com/studio/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://knowledgebase.fabricdata.com/studio/origin-studio-mcp-server/origin-studio-mcp-server.md).

# Origin Studio MCP Server

One unified MCP server spans **Origin Studio and Origin Nexus**: agents query and manage source-of-truth title metadata, catalog records, credits, availability, deliveries, and governance. **Tool access is governed by the authenticated identity's Studio permission groups** — a metadata-read agent and a catalog-write agent operate under different, auditable grants against the same server.

{% hint style="info" %}
**Access model:** OAuth 2.1 via enterprise identity (Auth0), multi-tenant by organization. The identity that authenticates determines which tools are available, mapped to that identity's Studio permission groups and tenant. All actions are attributable and audit-logged.
{% endhint %}

## Connect

|                     |                                                                                                                                                   |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Server URL**      | `https://mcp-api.studio.fabricdata.com`                                                                                                           |
| **Transport**       | Streamable HTTP                                                                                                                                   |
| **Auth**            | OAuth 2.1 via Auth0. Interactive agents use Authorization Code + PKCE (S256); headless agents use the Client Credentials (service-account) grant. |
| **Tenancy**         | Multi-tenant by Auth0 Organization — each customer is a governed, isolated tenant.                                                                |
| **Scopes / access** | Audience `https://studio.fabricdata.com`. Tool-level access is enforced per identity via Studio permission groups.                                |
| **Provisioning**    | Integration partners and agent platforms are onboarded as governed tenants — contact your Fabric account team.                                    |

### OAuth endpoints (Auth0)

|                                 |                                                            |
| ------------------------------- | ---------------------------------------------------------- |
| **Issuer**                      | `https://fabric-studio-v2-prod.us.auth0.com/`              |
| **Authorization**               | `https://fabric-studio-v2-prod.us.auth0.com/authorize`     |
| **Token**                       | `https://fabric-studio-v2-prod.us.auth0.com/oauth/token`   |
| **Dynamic Client Registration** | `https://fabric-studio-v2-prod.us.auth0.com/oidc/register` |
| **Audience**                    | `https://studio.fabricdata.com`                            |

**Interactive (Authorization Code + PKCE):**

```bash
claude mcp add origin-studio https://mcp-api.studio.fabricdata.com --transport http
# Complete the Auth0 organization login in your browser; tool availability reflects your grants.
```

**Headless (Client Credentials / service account):** agents that run unattended obtain a token directly from Auth0 using a client ID/secret issued for your tenant, scoped to the `https://studio.fabricdata.com` audience — no interactive login required. Contact your Fabric account team to provision service-account credentials.

Start every session with `whoami` to confirm identity, tenant, and effective permissions.

## Tool catalog

### Records & catalog (the source of truth)

`create_record` · `find_record` · `find_records` · `find_global_record` · `delete_record` · `permanently_delete_record` · `manage_record_core_attributes` · `manage_record_metadata` · `find_record_fields` · `find_record_children` · `find_record_compilations` · `manage_compilation_members` · `find_compilation_members` · `find_record_external_data` · `find_record_layouts` · `manage_record_layout`

Full CRUD over title/episode records, hierarchies, compilations, and metadata.

### Nexus enrichment & discovery

`search_origin_nexus` · `create_record_from_nexus` · `import_record_image_from_nexus`

Agents search the Nexus catalog and instantiate enriched Studio records directly from it — the unified-server workflow.

### Credits & contributors

`create_credit` · `find_credits` · `delete_credit` · `create_credit_list` · `manage_credit_list` · `find_credit_lists` · `manage_record_credits` · `create_contributor` · `find_contributor` · `find_contributors` · `manage_contributor` · `delete_contributor` · `find_contributor_credits` · `search_contributors` · `search_global_contributors`

### Lifecycle & workflow

`find_record_lifecycle` · `find_record_lifecycle_transitions` · `transition_record_lifecycle` · `manage_lifecycle_definition`

Agents move records through governed lifecycle states — with transitions constrained by the lifecycle definitions administrators configure.

### Media & assets

`upload_record_media` · `find_record_media` · `manage_record_media` · `archive_record_media` · `find_record_poster` · `find_media_storage`

### Deliveries & distribution

`manage_delivery` · `find_delivery` · `find_deliveries` · `delete_delivery` · `export_delivery` · `find_delivery_records` · `manage_delivery_records`

### Datasets & bulk operations

`create_dataset` · `find_dataset` · `find_datasets` · `manage_dataset` · `delete_dataset` · `create_dataset_item` · `manage_dataset_items` · `import_file_get_template` · `import_file_upload` · `import_file_scan_columns` · `import_file_start` · `import_file_status` · `find_background_job`

Template-driven bulk imports with column scanning and async job monitoring.

### Fields & schema

`create_field` · `find_field` · `manage_field` · `delete_field`

Configuration-as-code: agents can inspect and manage the metadata schema itself, under appropriate grants.

### Governance, permissions & audit

`whoami` · `find_users` · `find_roles` · `create_permission_group` · `find_permission_group` · `find_permission_groups` · `manage_permission_group` · `delete_permission_group` · `manage_record_permission_groups` · `create_policy_template` · `find_policy_template` · `find_policy_templates` · `manage_policy_template` · `assign_policy_template` · `find_policies` · `find_template_policies` · `delete_policy` · `delete_policies` · `query_audit_log` · `get_audit_query_results`

Machine-operable administration: permission groups, policy templates, and a queryable audit log.

### Machine identity & eventing

`create_api_key` · `find_api_key` · `find_api_keys` · `delete_api_key` · `create_event_subscription` · `find_event_subscription` · `find_event_subscriptions` · `delete_event_subscription`

Agents provision API keys and event subscriptions programmatically — webhook-style eventing without UI dependency.

### Utilization & observability

`find_utilization` · `find_utilization_snapshots`

## Example agent session

> **Goal:** onboard a new title from Nexus, credit the cast, and stage it for delivery.

```
1. whoami                                   → confirm tenant + grants
2. search_origin_nexus {title: "..."}       → find the enriched source record
3. create_record_from_nexus {...}           → instantiate the Studio record
4. import_record_image_from_nexus {...}     → attach key art
5. manage_record_credits {...}              → apply credits
6. transition_record_lifecycle {...}        → move to "Ready for Delivery"
7. manage_delivery_records {...}            → add to the distribution batch
8. query_audit_log {...}                    → verify the trail
```

## Errors, retries, and safety

* Structured, field-level validation errors on writes.
* `find_*` tools are always safe to retry; for writes, re-query before retrying. Destructive tools (`permanently_delete_record`) require elevated grants and should be excluded from most agent scopes.
* Async operations (imports, background jobs) expose status polling via `import_file_status` / `find_background_job`.

## See also

* [Origin Studio REST API](https://api.studio.fabricdata.com) — production API domain
* [Origin Nexus enrichment API](https://developer.iva-api.com/)
* EIDR compatibility, ISO/IEC 27001 certification — see [Agent Governance](https://www.fabricdata.com/agent-governance)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://knowledgebase.fabricdata.com/studio/origin-studio-mcp-server/origin-studio-mcp-server.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.