> For the complete documentation index, see [llms.txt](https://docs.unitlab.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unitlab.ai/api-sdk-cli/get-started/developer-overview.md).

# Developer overview

Choose Unitlab MCP for AI assistants, or the Python SDK, CLI, and authenticated HTTP API for data annotation pipelines and automation.

## One platform, four automation surfaces

```mermaid
flowchart LR
  AI["AI assistants"] --> MCP["MCP with OAuth"]
  APP["Applications and workers"] --> SDK["Python SDK"]
  OPS["Shell, CI, and runbooks"] --> CLI["CLI"]
  EXT["Other runtimes"] --> HTTP["Authenticated HTTP API"]
  SDK --> PLATFORM["Unitlab platform API"]
  CLI --> PLATFORM
  HTTP --> PLATFORM
  MCP --> PLATFORM
  PLATFORM --> RES["Projects · Data · Workflows · Queues · Releases"]
```

*Choose the integration surface by runtime and operating model. These surfaces provide access to Unitlab resources through their respective authentication and permission models.*

{% hint style="info" %}
**Outcome:** Choose MCP for conversational AI workflows, or the Python SDK, CLI, or authenticated HTTP interface for application and pipeline automation.
{% endhint %}

## Supported surfaces

| Surface                                                | Best fit                                                         | Contract                                                        |
| ------------------------------------------------------ | ---------------------------------------------------------------- | --------------------------------------------------------------- |
| [Unitlab MCP](https://docs.unitlab.ai/api-sdk-cli/mcp) | AI assistants working with projects, data, labels, and workflows | Remote Streamable HTTP with OAuth and member-scoped permissions |
| Python SDK                                             | Applications, notebooks, workers, data pipelines                 | Typed resource handles and exceptions                           |
| CLI                                                    | Shell workflows, CI jobs, operator runbooks                      | Human output or machine-readable JSON                           |
| HTTP API                                               | Runtimes where Python and the CLI cannot be used                 | Authenticated JSON requests to the SDK API routes               |

The Python SDK and CLI cover projects, Data Units, Batch Queues, Assets, folders, cloud storage, Data Groups, datasets and versions, custom embedding spaces, ontologies, workflow tasks, and releases. The current package requires Python 3.10 or newer.

## Start with MCP

Use MCP when you want an AI assistant to inspect data, create projects, upload image folders, label supported objects, coordinate review, or export a dataset through a conversation. The assistant connects to `https://api.unitlab.ai/mcp`, then you sign in with OAuth and approve one workspace, an access level, and any permission limits. This flow does not require a Unitlab API key.

Follow [Connect your AI assistant](https://docs.unitlab.ai/api-sdk-cli/mcp/connect-your-assistant), then try the [MCP quickstart](https://docs.unitlab.ai/api-sdk-cli/mcp/quickstart). The [MCP tool reference](https://docs.unitlab.ai/api-sdk-cli/mcp/tools) and [workflow guide](https://docs.unitlab.ai/api-sdk-cli/mcp/workflows) describe the available operations and their limits.

Choose the SDK, CLI, or HTTP API for explicitly programmed integrations and pipeline jobs. Their package, configuration, and API-key contracts below remain separate from MCP authorization.

## Resource model

```mermaid
flowchart LR
  C["UnitlabClient"] --> P["Projects"]
  C --> A["Assets & folders"]
  C --> D["Datasets & versions"]
  C --> E["Embedding spaces"]
  C --> O["Ontologies"]
  C --> R["Releases"]
  C --> S["Cloud storage"]
  P --> W["Workflow tasks"]
  P --> B["Batch Queues"]
```

Use the highest-level public method that expresses the operation. The resource handles normalize identifiers, translate product terms, page list responses, and map HTTP failures to typed exceptions.

## SDK, CLI, and HTTP API operating contract

| Concern           | Required behavior                                                                |
| ----------------- | -------------------------------------------------------------------------------- |
| Execution surface | Pinned `unitlab==3.1.3` application environment on Python 3.10+.                 |
| Identity          | Least-privilege API key supplied through approved configuration.                 |
| Target resolution | Stable resource IDs and an explicitly bounded target set.                        |
| Success evidence  | Typed return fields, server-side state, and downstream acceptance of the result. |

## Failure and recovery boundary

| Condition                                       | Response                                                                                                     |
| ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| Authentication or authorization fails           | Stop, correct the service identity or access model, rotate exposed credentials, and rerun a read-only check. |
| Validation or entitlement rejects the operation | Correct the input or entitlement; do not retry an unchanged request.                                         |
| A request times out                             | Inspect remote state before repeating a mutation because the server may have accepted it.                    |
| Asynchronous processing exceeds its deadline    | Preserve the Batch Queue or release ID, continue bounded monitoring, and inspect item-level failures.        |
| Only part of a batch succeeds                   | Keep successful identifiers, isolate failed rows, and retry only the corrected subset.                       |

{% hint style="warning" %}
Pin and test the production SDK version. Use stable IDs, keep secrets out of logs and command history, and record the correlation ID, target IDs, counts, final state, and redacted error details for material state changes.
{% endhint %}

***

> **Related Unitlab capability guides:** [Unitlab’s data annotation platform](https://unitlab.ai/en/data-annotation) and [Unitlab MCP for AI assistants](https://unitlab.ai/en/mcp).