> 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/mcp.md).

# MCP Server

Connect the exact AI client, verify authentication with a read-only call, and select a supported task.

Start with [client setup](/start-with-an-ai-agent/mcp/setup.md), then ask your assistant to call `blotato_list_accounts`. A successful response lists accounts or returns an empty array. Follow an [agent workflow](/agent-workflows/agent-workflows.md) after setup.

The Blotato MCP Server lets you control your social media workflows directly from AI tools like ChatGPT, Claude.ai, Claude Desktop, Claude Code, Cursor, Antigravity, and Replit Agent.

The MCP server runs remotely. The selected client determines its configuration, authorization, and installation requirements. A browser-hosted client does not require a local client installation. Follow [client setup](/start-with-an-ai-agent/mcp/setup.md), then verify a read-only tool result.

## What You Get

* Post to any connected social platform with a single prompt
* Schedule posts to your content calendar
* View, update, reschedule, and delete scheduled posts
* Extract content from YouTube videos, articles, tweets, and more
* Obtain signed upload URLs for local files, then transfer the bytes with the client's HTTP tool
* Check the status of your posts
* Compare top-performing posts and review engagement analytics
* Read and post comments on your Instagram and Facebook posts
* Read and send Instagram and Facebook DMs, with buttons or quick replies
* Create DM automations that reply for you when someone comments on your post or messages you

## Tutorials

* [Claude + Blotato Beginner Setup](https://www.youtube.com/watch?v=1dSNfnFL40c)
* [Build Your AI Personal Assistant for Social Media Marketing](https://youtu.be/3HVH2Iuplqo)
* [The ULTIMATE Claude Code Tutorial](https://youtu.be/fYX6hHC9FhQ)

For Claude Code-specific tutorials, see [Claude Code](/integrations-and-automation-templates/claude-code.md).

## Quick Setup

1. Connect your social accounts in [Accounts](https://my.blotato.com/accounts)
2. Add the Blotato MCP server to your AI tool (see [Setup Guide](/start-with-an-ai-agent/mcp/setup.md))

**MCP Server URL**: `https://mcp.blotato.com/mcp`

**REST API base URL** (for non-MCP HTTP clients): `https://backend.blotato.com/v2`

`api.blotato.com` is **not a valid base URL**. If your AI tool reports a DNS error for `api.blotato.com`, it guessed wrong. Use the URLs above.

**Auth**: OAuth or API key authentication, depending on the client configuration. Claude Code supports the OAuth flow in the [Setup Guide](/start-with-an-ai-agent/mcp/setup.md). The server also accepts `blotato-api-key` or `Authorization: Bearer <API_KEY>` headers. See [Authentication](/api-and-mcp-concepts/authentication.md).

For step-by-step setup instructions, see the [Setup Guide](/start-with-an-ai-agent/mcp/setup.md).

For all available tools and parameters, see the [Tools Reference](/start-with-an-ai-agent/mcp/tools.md).

For example prompts and multi-step workflows, see [Example Prompts](/start-with-an-ai-agent/mcp/examples.md).

Deciding between MCP and plain HTTP calls? See [Should I use the REST API or MCP?](/start-with-an-ai-agent/faqs.md#should-i-use-the-rest-api-or-mcp).


---

# 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/start-with-an-ai-agent/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.