Taisly Agent
@taisly
About Taisly Agent
Taisly Agent is an MCP server, CLI, SDK, and agent skill for publishing short-form videos to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook through Taisly. It helps AI agents and automation workflows validate connected social accounts, create video posts, and check publ
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"taisly": {
"command": "npx",
"args": [
"-y",
"@taisly/agent",
"mcp"
],
"env": {
"TAISLY_API_KEY": "<YOUR_TAISLY_API_KEY>"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Taisly Agent?
Taisly Agent is a JSON-first SDK, CLI, Agent Skill, and MCP server that lets AI agents, developer tools, and automation workflows publish videos to TikTok, Instagram Reels, YouTube Shorts, X, Facebook, and other connected social platforms through Taisly. It is designed for developers who need a reliable video publishing API to put AI‑generated content online.
How to use Taisly Agent?
Install globally with npm install -g @taisly/agent, then run npx @taisly/agent help or start the stdio MCP server with npx @taisly/agent mcp. Authentication requires setting the TAISLY_API_KEY environment variable. Use CLI commands like taisly auth:status, taisly platforms:list, taisly posts:validate, and taisly posts:create. MCP clients can connect via the taisly tool with the @taisly/agent mcp command.
Key features of Taisly Agent
- JSON‑first CLI and SDK for agentic video publishing.
- Stdio MCP server with nine tools (e.g.,
taisly_posts_create). - Built‑in agent skill enforcing a safe workflow: auth → platforms → validate → confirm → create → status.
- Cross‑platform posting to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook.
- Supports scheduling, local file validation, and JSON payload files.
- Works with Codex, Claude Code, Cursor, OpenClaw, and custom agents.
Use cases of Taisly Agent
- AI agent publishes a demo video or launch clip to multiple social accounts after user confirmation.
- Automate video publishing from a local file to TikTok, Instagram Reels, and YouTube Shorts in one CLI command.
- Add TikTok API posting automation to developer tools and content workflows without building platform integrations.
- Schedule a campaign of short‑form videos across connected accounts with a single JSON payload.
- Give an agent a safe, step‑by‑step posting path that validates payloads and requires explicit approval.
FAQ from Taisly Agent
What does Taisly Agent do that alternatives do not?
It provides a JSON‑first SDK, CLI, Agent Skill, and MCP server specifically designed for agentic social media posting, with a safe workflow that requires explicit user confirmation before publishing.
What are the runtime requirements?
A Taisly account, a Taisly API key set as the TAISLY_API_KEY environment variable, and Node.js. The video path must point to a real local file with supported extensions (.mp4, .mov, .avi, .mkv, .webm, .flv, .mpeg, .mpg).
Where does the data live?
Connected social accounts and posting execution are handled by Taisly. The agent sends video files and metadata to the Taisly API; post status is read from Taisly’s history.
What are the current limits?
The MCP server uses stdio transport only (remote transport planned later). posts:status reads from recent history because a single‑post endpoint is not yet available. posts:validate is a local preflight; final validation occurs in Taisly.
How does authentication work?
Set the TAISLY_API_KEY environment variable (obtained from Taisly Settings). The optional TAISLY_API_URL can target a non‑default Taisly API environment.
More AI & Agents MCP servers
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Comments