> For the complete documentation index, see [llms.txt](https://help.blotato.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.blotato.com/start-with-an-ai-agent/llm.md).

# API reference for agents

Start with the [agent quickstart](/start-with-an-ai-agent/agents.md). Use this page to retrieve the reference for the task. Detailed examples and FAQ material remain available through the links below.

## Choose the connected interface

| Interface                                               | Entry                                                                                                                            |
| ------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
| MCP tools such as `blotato_list_accounts` are available | Call the tools directly using their schemas. Read [MCP tools](/start-with-an-ai-agent/mcp/tools.md).                             |
| Your integration makes HTTP requests                    | Use `https://backend.blotato.com/v2` and the `blotato-api-key` header. Read [REST quickstart](/start-with-an-ai-agent/start.md). |
| No connection exists yet                                | Follow [client setup](/start-with-an-ai-agent/mcp/setup.md).                                                                     |

## Find the reference for the task

| Task                                           | Workflow                                                               | Compact reference                                                                                                   |
| ---------------------------------------------- | ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| Connect and authenticate                       | [Authentication](/api-and-mcp-concepts/authentication.md)              | [Endpoint and tool index](/start-with-an-ai-agent/llm/overview.md)                                                  |
| Select accounts, Pages, boards, or playlists   | [Identifiers](/api-and-mcp-concepts/accounts-and-identifiers.md)       | [Account lookup](/start-with-an-ai-agent/llm/accounts.md)                                                           |
| Publish or cross-post                          | [Publish and verify](/agent-workflows/agent-workflows/publish.md)      | [Publishing requests](/start-with-an-ai-agent/llm/publishing.md)                                                    |
| Generate a visual                              | [Create a visual](/agent-workflows/agent-workflows/visuals.md)         | [Visual requests](/start-with-an-ai-agent/llm/visuals.md)                                                           |
| Extract source content                         | [Repurpose content](/agent-workflows/agent-workflows/sources.md)       | [Source requests](/start-with-an-ai-agent/llm/sources.md)                                                           |
| Schedule or edit a post                        | [Scheduling](/api-and-mcp-concepts/scheduling.md)                      | [Schedules and slots](/start-with-an-ai-agent/llm/scheduling.md)                                                    |
| Read or reply to comments                      | [Comments workflow](/agent-workflows/agent-workflows/comments.md)      | [Comment requests](/start-with-an-ai-agent/llm/comments.md)                                                         |
| Read or reply to messages                      | [Messages workflow](/agent-workflows/agent-workflows/messages.md)      | [Message requests](/start-with-an-ai-agent/llm/messages.md)                                                         |
| Manage DM automations                          | [Automation workflow](/agent-workflows/agent-workflows/automations.md) | [Automation requests](/start-with-an-ai-agent/llm/automations.md)                                                   |
| Check plan or request limits                   | [Rate limits](/api-and-mcp-concepts/rate-limits.md)                    | [Plan limits](/start-with-an-ai-agent/llm/limits.md)                                                                |
| Combine extraction, generation, and publishing | [Workflow examples](/api-and-mcp-concepts/workflows.md)                | [Workflow and common mistakes](/start-with-an-ai-agent/llm/workflow.md)                                             |
| Read analytics                                 | [Analytics workflow](/agent-workflows/agent-workflows/analytics.md)    | [Analytics API](/rest-api-reference/analytics.md) and [metrics](/rest-api-reference/analytics/analytics-metrics.md) |
| Upload a local file                            | [Upload workflow](/agent-workflows/agent-workflows/upload.md)          | [Upload Media](/rest-api-reference/publish-post/upload-media-v2-media.md)                                           |
| Check or buy credits                           | [Credits workflow](/agent-workflows/agent-workflows/credits.md)        | [Credits reference](/rest-api-reference/credits.md)                                                                 |

## Execution rules

1. Get account and destination IDs from responses before publishing.
2. Follow the selected [platform's requirements](/platform-publishing/platforms.md).
3. Use MCP argument shapes for tools and REST body shapes for HTTP.
4. Pass public media URLs directly. Complete a presigned PUT upload for local files.
5. Save submission and creation IDs. Use [operation-specific completion rules](/api-and-mcp-concepts/async-jobs-and-polling.md).
6. Stop visual polling if `item.error` is set, including in an intermediate state.
7. Treat a scheduled response as scheduled. Report the resolved time.
8. Return the actual result and public URL when available. Check existing work before retrying an uncertain create request.

For errors, use [Errors and retries](/api-and-mcp-concepts/error-handling.md), [API FAQs](/start-with-an-ai-agent/faqs.md), and [MCP FAQs](/start-with-an-ai-agent/mcp/faqs.md).

## Machine-readable sources

* [Documentation index](https://help.blotato.com/llms.txt)
* [Full documentation text](https://help.blotato.com/llms-full.txt)
* [OpenAPI JSON](https://backend.blotato.com/openapi.json)
* [This page as Markdown](https://help.blotato.com/api/llm.md)

Use OpenAPI for REST schemas. Use the connected MCP tool schemas for tool calls. These interfaces do not have identical operation coverage.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.blotato.com/start-with-an-ai-agent/llm.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.