> 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/api-and-mcp-concepts/rest-vs-mcp.md).

# REST versus MCP

Choose REST or MCP and keep authentication, request nesting, polling, and capability differences separate.

Both interfaces use your Blotato account and subscription. Choose the interface your assistant or automation uses.

|                                      | MCP                                                                          | REST API                                                                   |
| ------------------------------------ | ---------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
| Use from                             | An assistant with MCP tools                                                  | HTTP code, n8n, Make, or other workflow tools                              |
| Connect to                           | `https://mcp.blotato.com/mcp`                                                | `https://backend.blotato.com/v2`                                           |
| Authenticate                         | OAuth or an API key, depending on the client                                 | `blotato-api-key` header                                                   |
| Publish input                        | Tool arguments such as `accountId`, `platform`, `text`, and `mediaUrls`      | A JSON body containing `post.accountId`, `post.content`, and `post.target` |
| Account lookup                       | `blotato_list_accounts` includes subaccounts                                 | Fetch accounts, then fetch subaccounts when needed                         |
| Immediate post and source completion | Tools wait internally for up to 20 seconds, then return the available result | Submit, save the returned ID, and poll the status endpoint                 |
| Visual completion                    | Call `blotato_get_design_status`                                             | Poll the visual status endpoint                                            |
| Reference                            | [MCP tools](/start-with-an-ai-agent/mcp/tools.md)                            | [OpenAPI](/rest-api-reference/openapi-reference.md)                        |

MCP tools expose a selected set of workflows. An endpoint in OpenAPI does not imply a corresponding MCP tool. For example, REST includes schedule-slot management and a [webhook publishing target](/rest-api-reference/publish-post.md#webhook). MCP manages scheduled posts and publishes to the 9 listed social platforms, but does not expose these 2 REST capabilities.

## Choose your setup

1. If your assistant already has `blotato_` tools, call those tools directly using their schemas.
2. If you are adding Blotato to an assistant, follow [MCP setup](/start-with-an-ai-agent/mcp/setup.md).
3. If you are building HTTP requests, follow the [REST quickstart](/start-with-an-ai-agent/start.md).
4. If you use workflow software, follow the [n8n](/integrations-and-automation-templates/n8n.md) or [Make](/integrations-and-automation-templates/make.com.md) guide.

Keep the 2 request shapes separate. Copying a REST `post` object into an MCP tool call fails when the tool expects flat arguments.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.blotato.com/api-and-mcp-concepts/rest-vs-mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.