# Interface reference

Use reference pages to look up command syntax, configuration fields, responses, and events. For a first execution, follow the [quickstart](https://flowllm-ai.github.io/AxonX/en/getting-started/quickstart); for a complete research chain, follow the [research workflow](https://flowllm-ai.github.io/AxonX/en/research/workflow).

## Choose an interface

| Interface or setting                           | Reference                                                 |
| ---------------------------------------------- | --------------------------------------------------------- |
| Shell commands and local execution             | [CLI](https://flowllm-ai.github.io/AxonX/en/reference/cli)                                             |
| Programmatic service calls                     | [Python](https://flowllm-ai.github.io/AxonX/en/reference/python)                                       |
| Client addresses, tokens, and timeouts         | [Client configuration](https://flowllm-ai.github.io/AxonX/en/reference/client-configuration)           |
| Application, component, and Job assembly       | [Server configuration](https://flowllm-ai.github.io/AxonX/en/reference/configuration)                  |
| HTTP discovery and JobResponse                 | [API overview](https://flowllm-ai.github.io/AxonX/en/api/overview)                        |
| Task submission, state, context, and graphs    | [Task API](https://flowllm-ai.github.io/AxonX/en/api/tasks)                               |
| Live progress and log events                   | [SSE events](https://flowllm-ai.github.io/AxonX/en/api/events)                            |
| Workspace listing and previews                 | [Workspace API](https://flowllm-ai.github.io/AxonX/en/api/workspace)                      |
| Machines and resource readings                 | [Machine API](https://flowllm-ai.github.io/AxonX/en/api/machines)                         |
| Plugin management and snapshot synchronization | [Plugins and synchronization API](https://flowllm-ai.github.io/AxonX/en/api/plugins-sync) |
| Built-in Agent sessions                        | [Agent API](https://flowllm-ai.github.io/AxonX/en/api/agent)                              |

External agents discover service tools through [MCP integration](https://flowllm-ai.github.io/AxonX/en/agent/mcp-integration). MCP exposes public Jobs; live SSE uses the HTTP event endpoints.

## Read responses at the right layer

HTTP transport status, JobResponse `success`, and Task terminal state answer different questions. A successful `submit` returns a TaskHandle; use its `task_id` and `run_id` to wait for that execution and inspect its final state. Discover schemas on the connected service because installed plugins and configured Jobs determine available capabilities.

For implementation contracts, see [Task contracts](https://flowllm-ai.github.io/AxonX/en/reference/task-contracts), [plugin manifests](https://flowllm-ai.github.io/AxonX/en/reference/plugin-manifest), and [research artifacts](https://flowllm-ai.github.io/AxonX/en/reference/research-artifacts) under [Developers](https://flowllm-ai.github.io/AxonX/en/development/overview). For execution semantics, see [Jobs and Tasks](https://flowllm-ai.github.io/AxonX/en/concepts/jobs-and-tasks).