TikTok Agent Publisher MCP Server
io.github.davidmosiah/tiktok-agent-publisher
What this kind of tool is for
- Chain multi-step workflows across the other tools in this directory.
- Run a scheduled or triggered job instead of retyping the same request.
- Have your agent watch a feed, queue, or repo and act on new items.
How to compare servers like this
- Trigger model:
- Understand what starts the automation — a command, a schedule, or an event — before relying on it.
- Blast radius:
- Prefer tools that hand you a review point before an irreversible action runs.
- Chaining cost:
- Each chained step adds a failure point; keep critical paths on the fewest tools.
- Maintenance signal:
- Automations break quietly; a maintained tool is the difference between repair and rediscovery.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the TikTok Agent Publisher MCP server?
Local-first TikTok Content Posting API for AI agents: OAuth checks, dry-run and live uploads.
How to install TikTok Agent Publisher
Copy-paste configuration for popular MCP clients.
TIKTOK_DRY_RUNSet to false only when the agent should perform live TikTok upload operations. Defaults to dry-run behavior.
TIKTOK_CLIENT_KEYTikTok developer app client key. Optional until OAuth or live upload flows are used.
TIKTOK_CLIENT_SECRETsecretTikTok developer app client secret. Keep local and do not expose it to agents.
{
"mcpServers": {
"tiktok-agent-publisher": {
"command": "npx",
"args": [
"-y",
"tiktok-agent-publisher"
],
"env": {
"TIKTOK_DRY_RUN": "<YOUR_TIKTOK_DRY_RUN>",
"TIKTOK_CLIENT_KEY": "<YOUR_TIKTOK_CLIENT_KEY>",
"TIKTOK_CLIENT_SECRET": "<YOUR_TIKTOK_CLIENT_SECRET>"
}
}
}
}Related MCP servers
Source-aware archive for timeline-shift folklore, Mandela Effect reports, and collider myths.

Search and map the Pentagon UAP/UFO releases plus curated official archives from 12 nations.
Local-first air-quality MCP for AI agents — AirGradient, AirThings, PurpleAir, IQAir, Awair.
Local-first CGM MCP for AI agents: Dexcom Developer API + FreeStyle Libre via LibreLink Up.
Local-first cycle coach MCP for phase-aware nutrition and training context.
Local-first nutrition MCP for AI agents: food, barcode, photo, intake, hydration, goals.