> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Using the API

> Call the AgentOS API to run agents, teams, and workflows.

AgentOS exposes endpoints for running agents and managing sessions, memories, knowledge, and evals. The same API powers the [control plane](/agent-os/control-plane) and can be used to build your AI products.

## Instance Discovery

`GET /info` is unauthenticated and returns what a client needs to bootstrap against an instance: which authentication mode it enforces and whether an MCP server is mounted.

```bash theme={null}
curl http://localhost:7777/info
```

```json theme={null}
{
  "os_id": "my-agent-os",
  "name": null,
  "agno_version": "2.7.2",
  "agent_count": 1,
  "team_count": 0,
  "workflow_count": 0,
  "mcp": {
    "enabled": true,
    "path": "/mcp",
    "oauth": null
  },
  "auth_mode": "none"
}
```

| Field                                         | Description                                                                        |
| --------------------------------------------- | ---------------------------------------------------------------------------------- |
| `auth_mode`                                   | Authentication enforced by the instance: `none`, `security_key`, or `jwt`          |
| `mcp.enabled`                                 | Whether the MCP server is mounted                                                  |
| `mcp.path`                                    | Mount path of the MCP server, `null` when disabled                                 |
| `mcp.oauth`                                   | OAuth discovery details when the MCP endpoint is OAuth-protected, `null` otherwise |
| `agent_count`, `team_count`, `workflow_count` | Registered components                                                              |
| `agno_version`                                | Agno version running on the instance                                               |

## Endpoints

| Resource  | Operations                             |
| --------- | -------------------------------------- |
| Agents    | Run, list, get                         |
| Teams     | Run, list, get                         |
| Workflows | Run, list, get                         |
| Sessions  | Create, list, get, update, delete      |
| Memories  | Create, list, get, update, delete      |
| Knowledge | Add, search, list, get, update, delete |
| Evals     | Create, list, get, update, delete      |
| Metrics   | Get, refresh                           |

See the [API reference](/reference-api/overview) for full documentation.

## Running Agents

```bash theme={null}
curl http://localhost:7777/agents/my-agent/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Tell me about Agno" \
  -d "stream=true" \
  -d "user_id=john@example.com" \
  -d "session_id=session_123"
```

Teams and workflows follow the same pattern:

* `POST /teams/{team_id}/runs`
* `POST /workflows/{workflow_id}/runs`

## Authentication

The `auth_mode` field from `GET /info` tells you which credential to send:

| `auth_mode`    | Credential                                |
| -------------- | ----------------------------------------- |
| `none`         | No header required                        |
| `security_key` | `Authorization: Bearer <OS_SECURITY_KEY>` |
| `jwt`          | `Authorization: Bearer <jwt-token>`       |

```bash theme={null}
curl http://localhost:7777/agents/my-agent/runs \
  -H "Authorization: Bearer <your-token>" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Your query here"
```

Service-account tokens (`agno_pat_...`) are accepted as bearer credentials in every mode on instances with a database. See [Security & Authorization](/agent-os/security/overview) to configure authentication.

## Passing Dependencies

Pass runtime parameters like `dependencies`, `session_state`, or `metadata` as form fields:

```bash theme={null}
curl http://localhost:7777/agents/story-writer/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Write me a 5 line story" \
  -d 'dependencies={"robot_name": "Anna"}'
```

## Output Schema

Pass a JSON schema to structure the response:

```bash theme={null}
curl http://localhost:7777/agents/story-writer/runs \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "message=Write a story" \
  -d 'output_schema={"type":"object","properties":{"title":{"type":"string"},"content":{"type":"string"}},"required":["title","content"]}'
```

## Cancelling Runs

```bash theme={null}
curl -X POST http://localhost:7777/agents/story-writer/runs/123/cancel
```