> 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/agents.md).

# Start here

Start here to connect an AI assistant to Blotato, verify access, and choose a workflow.

Connect your AI assistant to Blotato to publish and schedule social posts, generate visuals, read analytics, and manage comments and messages. You describe the task. Your assistant calls Blotato's tools.

## 1. Connect your social accounts

Open [Blotato Settings](https://my.blotato.com/settings) and connect the accounts you want to use. Follow the [account connection guide](/settings/social-accounts.md) for your platform.

Blotato API and MCP access requires a paid subscription. Generating an API key during a trial starts the paid subscription. Review [API access and authentication](/api-and-mcp-concepts/authentication.md) before generating a key.

## 2. Connect your assistant

Open the [MCP setup guide](/start-with-an-ai-agent/mcp/setup.md) and select your client. MCP lets your assistant call tools such as `blotato_list_accounts` without you writing HTTP requests.

For n8n, Make, or an agent making HTTP requests, use the [REST quickstart](/start-with-an-ai-agent/start.md). See [REST versus MCP](/api-and-mcp-concepts/rest-vs-mcp.md) if you are choosing an integration.

## 3. Verify the connection

Ask your assistant:

> List my connected Blotato accounts. Use `blotato_list_accounts` and show each account's platform, name, and ID.

A successful call returns your accounts, or an empty array if no accounts are connected. An empty result confirms access. Connect an account in Settings before publishing. A connector displaying “Connected” alone does not verify a tool call.

## 4. Choose a task

| Your task                                  | Instructions                                                                 |
| ------------------------------------------ | ---------------------------------------------------------------------------- |
| Publish a post or cross-post               | [Publish and verify a post](/agent-workflows/agent-workflows/publish.md)     |
| Schedule or edit a post                    | [Schedule and manage posts](/agent-workflows/agent-workflows/schedule.md)    |
| Upload a photo or video from your computer | [Upload local media](/agent-workflows/agent-workflows/upload.md)             |
| Generate an image, carousel, or video      | [Create and publish a visual](/agent-workflows/agent-workflows/visuals.md)   |
| Repurpose an article, video, or text       | [Extract and repurpose content](/agent-workflows/agent-workflows/sources.md) |
| Compare post performance                   | [Read analytics](/agent-workflows/agent-workflows/analytics.md)              |
| Read comments or reply                     | [Manage comments](/agent-workflows/agent-workflows/comments.md)              |
| Read or reply to a DM                      | [Manage messages](/agent-workflows/agent-workflows/messages.md)              |
| Send replies from comment keywords or DMs  | [Manage DM automations](/agent-workflows/agent-workflows/automations.md)     |
| Check credits or buy more                  | [Manage credits](/agent-workflows/agent-workflows/credits.md)                |

## Instructions for the agent

1. Use the connected MCP tools when available. Read the tool's input schema before calling it. Use REST only when working through HTTP.
2. Fetch the user's accounts before publishing. Get IDs from responses, including Page, board, playlist, and post IDs. Follow [Accounts and identifiers](/api-and-mcp-concepts/accounts-and-identifiers.md).
3. Follow the selected platform's [publishing requirements](/platform-publishing/platforms.md). Required media and target fields differ by platform.
4. For a public media URL, pass the URL directly. For a local file, complete the [upload flow](/api-and-mcp-concepts/media-uploads-and-conversion.md) first.
5. Record the returned submission or creation ID. Follow the operation's [completion rules](/api-and-mcp-concepts/async-jobs-and-polling.md). A submitted request is not proof of publication.
6. For scheduled posts, report the resolved time. For published posts, return the supplied public URL. For failures, explain the returned error and the next action.

## Documentation for retrieval

| Resource                                                          | Use                                       |
| ----------------------------------------------------------------- | ----------------------------------------- |
| [MCP tools](/start-with-an-ai-agent/mcp/tools.md)                 | Tool inputs, outputs, and behavior        |
| [API reference for agents](/start-with-an-ai-agent/llm.md)        | Compact API details and workflow examples |
| [Documentation index](https://help.blotato.com/llms.txt)          | Find relevant documentation pages         |
| [Full documentation text](https://help.blotato.com/llms-full.txt) | Read the full help corpus when needed     |
| [OpenAPI JSON](https://backend.blotato.com/openapi.json)          | Inspect REST request and response schemas |
| [API and MCP FAQs](/start-with-an-ai-agent/faqs.md)               | Answers to integration questions          |

GitBook also serves individual pages as Markdown. For example, read this page at [agents.md](https://help.blotato.com/api/agents.md). Start with the index and retrieve the pages for the task before loading the full corpus.

For web app instructions, see [Make your first 5 posts](/web-app-getting-started/posts.md). For errors, see [Troubleshooting](/api-and-mcp-concepts/error-handling.md).


---

# 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/agents.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.