A Model Context Protocol (MCP) server for TikTok Ads API integration. This server enables AI assistants like Claude to interact with TikTok advertising campaigns, providing comprehensive campaign management, analytics, and optimization capabilities. This project is part of the AdsMCP AI advertising automation platform, an AI-powered platform designed to simplify and automate ad campaign management
Add this skill
npx mdskills install AdsMCP/tiktok-ads-mcp-serverComprehensive TikTok Ads API integration with clear setup, useful tools, and good documentation
A Model Context Protocol (MCP) server for TikTok Ads API integration. This server enables AI assistants like Claude to interact with TikTok advertising campaigns, providing comprehensive campaign management, analytics, and optimization capabilities.
This project is part of the AdsMCP AI advertising automation platform, an AI-powered platform designed to simplify and automate ad campaign management across multiple advertising networks. The platform emphasizes efficiency, data-driven insights, and intelligent automation for marketers and agencies. Additionally, AdsMCP also supports integration with other advertising platforms, such as Google Ads and Meta (Facebook) Ads, making it easier to manage campaigns across multiple networks from a single interface.
# Clone the repository
git clone
cd adsmcp-server
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -e .
# Install with uv
uv sync
If you don’t want to host the server and set it up manually yourself, AdsMCP provides a remote MCP server. You can easily connect your ad accounts within one minute, without worrying about server configuration or dependencies. Visit the AdsMCP Remote MCP Server Setup Guide for a step-by-step tutorial to quickly connect your ad accounts.
Add to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"tiktok-ads": {
"command": "python",
"args": ["/path/to/adsmcp-server/run_server.py"],
"cwd": "/path/to/adsmcp-server",
"env": {
"TIKTOK_APP_ID": "your_app_id",
"TIKTOK_APP_SECRET": "your_app_secret",
}
}
}
}
tiktok_ads_login - Start TikTok Ads OAuth authentication flowtiktok_ads_complete_auth - Complete OAuth authentication with authorization codetiktok_ads_auth_status - Check current authentication statustiktok_ads_switch_ad_account - Switch to a different advertiser accounttiktok_ads_get_campaigns - Retrieve all campaigns for the advertiser accounttiktok_ads_get_campaign_details - Get detailed information about a specific campaigntiktok_ads_get_adgroups - Retrieve ad groups for a campaigntiktok_ads_get_campaign_performance - Get performance metrics for campaigns with detailed metrics supporttiktok_ads_get_adgroup_performance - Get performance metrics for ad groups with breakdownsRegister as Developer
Get API Credentials
OAuth Flow (for production)
TikTok Ads API has the following limits:
The server includes built-in rate limiting and retry logic.
The server provides comprehensive error handling:
This project is licensed under the MIT License - see the LICENSE file for details.
For issues and questions, please create an issue in this repository.
Install via CLI
npx mdskills install AdsMCP/tiktok-ads-mcp-serverTikTok Ads MCP Server is a free, open-source AI agent skill. A Model Context Protocol (MCP) server for TikTok Ads API integration. This server enables AI assistants like Claude to interact with TikTok advertising campaigns, providing comprehensive campaign management, analytics, and optimization capabilities. This project is part of the AdsMCP AI advertising automation platform, an AI-powered platform designed to simplify and automate ad campaign management
Install TikTok Ads MCP Server with a single command:
npx mdskills install AdsMCP/tiktok-ads-mcp-serverThis downloads the skill files into your project and your AI agent picks them up automatically.
TikTok Ads MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.