TikTok MCP server for AI agents

The TikTok MCP (Model Context Protocol) server enables AI assistants like Claude to interact with TikTok content. It allows you to analyze video virality factors, extract content from TikTok videos, and chat with TikTok videos through the TikNeuron service.

Requirements

Before installing the TikTok MCP server, ensure you have:

NodeJS v18 or higher (https://nodejs.org/)
Git (https://git-scm.com/)
TikNeuron Account and MCP API Key (https://tikneuron.com/tools/tiktok-mcp)

Installation

Follow these steps to set up the TikTok MCP server:

Clone the repository:

git clone https://github.com/Seym0n/tiktok-mcp.git

Install dependencies:

npm install

Build the project:

npm run build

This will create the file build\index.js which is needed to run the server.

Configuration with Claude AI

To use the TikTok MCP with Claude AI, add the following entry to your mcpServers configuration:

"tiktok-mcp": {
    "command": "node",
    "args": [
      "path\\build\\index.js"
    ],
    "env": {
      "TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
    }
}

Be sure to:

Replace path with the actual path to your TikTok MCP installation
Replace XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX with your TikNeuron API Key

Your final mcpServers configuration should look like this:

{
  "mcpServers": {
    "tiktok-mcp": {
      "command": "node",
      "args": [
        "path\\build\\index.js"
      ],
      "env": {
        "TIKNEURON_MCP_API_KEY": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
      }
    }
  }
}

Available Tools

The TikTok MCP provides three main tools:

tiktok_available_subtitles

This tool checks what subtitle content is available for a TikTok video. It returns information about available subtitles in different languages and formats (Automatic Speech Recognition, Machine Translation, or Creator Captions).

Input Parameters:

tiktok_url (required): TikTok video URL (e.g., https://www.tiktok.com/@username/video/1234567890 or https://vm.tiktok.com/1234567890)

tiktok_get_subtitle

This tool retrieves the subtitle or content for a specific TikTok video. If no language code is provided, it returns the automatic speech recognition subtitle.

Input Parameters:

tiktok_url (required): TikTok video URL
language_code (optional): Language code for the subtitle (e.g., en for English, es for Spanish, fr for French)

tiktok_get_post_details

This tool provides comprehensive details about a TikTok post, including:

Description
Creator username
Hashtags
Engagement metrics (likes, shares, comments, views, bookmarks)
Creation date
Video duration

Input Parameters:

tiktok_url (required): TikTok video URL

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.