tiktok-mcp
MCP server for TikTok that lets AI agents connect accounts, post and schedule videos, follow users, manage profiles, and analyze performance—all via QR login with no API keys.
README
TikTok MCP
Self-hosted TikTok automation for AI agents. Connect accounts, post and schedule videos, manage profiles, and track analytics through one local MCP server.
- Runs the browser and automation on your device
- Keeps TikTok sessions, media, and analytics local
- Works with any MCP-compatible agent or CLI
- No API keys, payments, or hosted dependency
Quick start
You need Node.js 18.18+ and Chrome, Edge, or Brave. Add this server to your agent's MCP configuration:
{
"mcpServers": {
"tiktok": {
"command": "npx",
"args": ["-y", "github:0xArtex/tiktok-mcp"]
}
}
}
Restart the agent, then ask:
Connect my TikTok account as my-brand.
A browser opens on your device. Sign in or scan TikTok's QR code; the agent can poll the connection while you finish. The persistent browser profile and state are stored under ~/.tiktok-mcp.
If no installed browser is detected, install Playwright's Chromium once:
npx playwright install chromium
Example prompts
Post launch.mp4 with the caption "We finally shipped."
Schedule demo.mp4 for tomorrow at 6 PM.
Show which of my recent videos are still gaining views.
Analyze the strongest hooks from my fitness posts.
Update my bio to "Building useful things in public."
Local paths are supported by tiktok_post (video_path) and tiktok_update_avatar (image_path). Public media URLs and base64 inputs also work.
Tools
| Tool | What it does |
|---|---|
tiktok_connect |
Open a local browser for TikTok login |
tiktok_connect_status |
Check whether login completed |
tiktok_accounts |
List local accounts and session state |
tiktok_post |
Post or natively schedule a video |
tiktok_operation_status |
Poll an asynchronous browser job |
tiktok_follow |
Follow a user |
tiktok_like |
Like a video |
tiktok_delete |
Delete a video |
tiktok_update_profile |
Update a display name or bio |
tiktok_update_avatar |
Update a profile image |
tiktok_analytics |
Collect and save post metrics locally |
tiktok_series |
Read saved performance history and growth |
tiktok_hooks |
Analyze caption hooks from local history |
tiktok_niches |
List suggested hook-analysis niches |
tiktok_scheduled |
List scheduled posts recorded locally |
tiktok_cancel_scheduled |
Cancel a scheduled post |
Hosted HTTP API
Don't want to run the browser/runtime yourself? Use the hosted x402 API at https://tiktok.palmyr.ai/v1 with AgentCash, Agentic Market, or any x402 client. It is an HTTP API, not a remote MCP server.
npx agentcash@latest add https://tiktok.palmyr.ai
npx agentcash@latest discover https://tiktok.palmyr.ai
npx agentcash@latest check https://tiktok.palmyr.ai/v1/post
AgentCash handles the x402 challenge and USDC payment:
npx agentcash@latest fetch https://tiktok.palmyr.ai/v1/connect \
-m POST \
-b '{"account_id":"my-brand"}'
The hosted service is optional. The local MCP never calls it.
Local configuration
| Setting | Default | Description |
|---|---|---|
TIKTOK_MCP_DATA_DIR |
~/.tiktok-mcp |
Local profiles, job state, and analytics |
TIKTOK_BROWSER_PATH |
auto-detected | Chrome-family browser executable |
TIKTOK_HEADLESS |
headed on desktop | Set true for headless operation |
Equivalent CLI flags are --data-dir, --browser-path, and --headless.
Development
git clone https://github.com/0xArtex/tiktok-mcp.git
cd tiktok-mcp
npm install
npm test
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.