# Get datasets

URL: https://docs.hanzo.ai/docs/openapi/eval/get-eval-datasets-by-name

> Returns one dataset of the caller's org by name, together with its live item count — the one read that answers how big the set actually is.

`GET /v1/eval/datasets/{name}`

> [Eval →](https://docs.hanzo.ai/docs/openapi/eval) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides)

|               |                                                |
| ------------- | ---------------------------------------------- |
| **Address**   | `https://api.hanzo.ai/v1/eval/datasets/{name}` |
| **Method**    | `GET`                                          |
| **Operation** | `get_eval_datasets_by_name`                    |
| **Auth**      | `Authorization: Bearer $HANZO_API_KEY`         |

Returns one dataset of the caller's org by name, together with its
live item count — the one read that answers how big the set actually is.

A name this org does not have is 404, which is also what another tenant's
dataset looks like from here. Requires a validated principal; 401 without one.

## Request

1 field.

| Field  | In   | Type   | Required | Description                        |
| ------ | ---- | ------ | -------- | ---------------------------------- |
| `name` | path | string | yes      | Name is the dataset the URL names. |

## Response

| Status    | Body             | Meaning |
| --------- | ---------------- | ------- |
| `200`     | eval.datasetView | ok      |
| `default` | problem-details  | refused |

`200` body — 7 fields.

| Field         | In   | Type            | Always | Description                                                                 |
| ------------- | ---- | --------------- | ------ | --------------------------------------------------------------------------- |
| `createdAt`   | body | string          | —      | CreatedAt is when the name was first written, kept across later edits.      |
| `description` | body | string          | —      | Description is free text the org wrote about what this set measures.        |
| `items`       | body | integer (int64) | —      | Items is how many examples the set holds.                                   |
| `metadata`    | body | object          | —      | Metadata is the free-form object stored with the set, echoed back verbatim. |
| `metadata.*`  | body | any             | —      |                                                                             |
| `name`        | body | string          | —      | Name is the dataset's org-unique handle and the segment that addresses it.  |
| `updatedAt`   | body | string          | —      | UpdatedAt is when the description or metadata last changed.                 |

Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors).

## Examples

**CLI**

```bash
hanzo eval datasets get <name>
```

**SDK**

**.ts**

```ts
import { Configuration, EvalApi } from 'hanzoai';

const api = new EvalApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getEvalDatasetsByName({ name: 'name' });
```

**.py**

```python
from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import EvalApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = EvalApi(client).get_eval_datasets_by_name(name='name')
```

**.go**

```go
cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.EvalAPI.GetEvalDatasetsByName(context.Background()).Execute()
if err != nil {
	return err
}
```

**.rs**

```rust
use hanzo_client::apis::{configuration::Configuration, eval_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = eval_api::get_eval_datasets_by_name(&cfg, Default::default()).await?;
```

**.java**

```java
import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.EvalApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new EvalApi(client).getEvalDatasetsByName();
```

**HTTP**

```bash
curl https://api.hanzo.ai/v1/eval/datasets/<name> \
  -H "Authorization: Bearer $HANZO_API_KEY"
```

**MCP**

MCP reaches **eval** through the `eval` tool, which names its 16 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them:

```bash
curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_eval_datasets"
         }
       }
     }'
```

---

[Eval API](https://docs.hanzo.ai/docs/openapi/eval) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)