# List kit

URL: https://docs.hanzo.ai/docs/openapi/tool/get-tool-kit

> Answers the caller's kit: what their coding runs carry of the org's tool plane.

`GET /v1/tool/kit`

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

|               |                                        |
| ------------- | -------------------------------------- |
| **Address**   | `https://api.hanzo.ai/v1/tool/kit`     |
| **Method**    | `GET`                                  |
| **Operation** | `get_tool_kit`                         |
| **Auth**      | `Authorization: Bearer $HANZO_API_KEY` |

Answers the caller's kit: what their coding runs carry of the org's tool
plane. Skills are the documents of those an admin of the org activated; servers
are those an admin registered, each by its id with the tools of it an admin
activated — never an address or a credential, which stay on the plane. Both
leave out what the caller muted, and muted names it. It is the one read a run
makes, so what it answers is what the caller's runs carry.

## Request

`GET /v1/tool/kit` takes no parameters and no body — the credential is the whole request.

## Response

| Status    | Body            | Meaning |
| --------- | --------------- | ------- |
| `200`     | tool.Kit        | ok      |
| `default` | problem-details | refused |

`200` body — 9 fields.

| Field              | In   | Type             | Always | Description                                                                                                             |
| ------------------ | ---- | ---------------- | ------ | ----------------------------------------------------------------------------------------------------------------------- |
| `excess`           | body | string\[]        | —      | Excess are servers left out, by id, because a run carries only so many.                                                 |
| `muted`            | body | string\[]        | —      | Muted are the names the run's person took out of their own runs — a skill, a server's tool, or a server by its id.      |
| `omitted`          | body | string\[]        | —      | Omitted are activated skills left out because a run carries only so many.                                               |
| `servers`          | body | tool.Remote\[]   | —      | Servers are the MCP servers an admin registered and activated tools of, at most KitServers of them.                     |
| `servers[].name`   | body | string           | —      | Name is the server's id in the org, which also prefixes its tools on the tool plane, and names it to ToolsRelay.        |
| `servers[].tools`  | body | string\[]        | —      | Tools are the tools of it an admin activated, each by the server's own name for it: all a run's harness may call of it. |
| `skills`           | body | tool.SkillDoc\[] | —      | Skills are the documents of the skills an admin activated, by name.                                                     |
| `skills[].content` | body | string           | —      | Content is the skill's SKILL.md, verbatim.                                                                              |
| `skills[].name`    | body | string           | —      | Name is the skill's bare name, which is also the directory its SKILL.md is written into.                                |

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

## Examples

**CLI**

`hanzo` has no subcommand for this operation — the CLI serves only what cloud's live route table confirms. Use HTTP or an SDK.

**SDK**

**.ts**

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

const api = new ToolApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getToolKit();
```

**.py**

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

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = ToolApi(client).get_tool_kit()
```

**.go**

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

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

**.rs**

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

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

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

**.java**

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

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

var result = new ToolApi(client).getToolKit();
```

**HTTP**

```bash
curl https://api.hanzo.ai/v1/tool/kit \
  -H "Authorization: Bearer $HANZO_API_KEY"
```

**MCP**

MCP reaches **tool** through the `tool` tool, which names its 17 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_tools"
         }
       }
     }'
```

---

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