{
  "markdown": "![Taisly Agent Kit: AI agent social media posting for TikTok, Instagram Reels, YouTube Shorts, X, and Facebook](assets/taisly-agent-banner.jpg)\n\n# Taisly Agent Kit\n\n[![Taisly MCP server](https://glama.ai/mcp/servers/taisly/agent/badges/card.svg)](https://glama.ai/mcp/servers/taisly/agent)\n[![Taisly MCP score](https://glama.ai/mcp/servers/taisly/agent/badges/score.svg)](https://glama.ai/mcp/servers/taisly/agent)\n\nFree AI-first social media posting for short-form video. Taisly Agent Kit 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.\n\nUse it when your agent can create content, write captions, or prepare a campaign, but still needs a reliable video publishing API to put that content online. The package is free to install and designed to get an agent from idea to published video without building every platform integration yourself.\n\n[Website](https://taisly.com/en) | [Agent Kit](https://taisly.com/en/ai-agent-kit) | [API Docs](https://docs.taisly.com/en/docs) | [npm](https://www.npmjs.com/package/@taisly/agent) | [GitHub](https://github.com/taisly/agent) | [MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.taisly%2Fagent) | [Glama](https://glama.ai/mcp/servers/taisly/agent) | [Guide](https://taisly.com/en/blog/ai-agent-social-media-posting-api)\n\n## Languages\n\nRead this guide in:\n[English](docs/i18n/README.en.md),\n[Español](docs/i18n/README.es.md),\n[Deutsch](docs/i18n/README.de.md),\n[Français](docs/i18n/README.fr.md),\n[Português](docs/i18n/README.pt-PT.md),\n[ไทย](docs/i18n/README.th.md),\n[中文](docs/i18n/README.zh-CN.md),\n[Bahasa Indonesia](docs/i18n/README.id.md),\n[Русский](docs/i18n/README.ru.md),\n[Nederlands](docs/i18n/README.nl.md),\n[한국어](docs/i18n/README.ko.md),\n[日本語](docs/i18n/README.ja.md),\n[العربية](docs/i18n/README.ar.md),\n[Türkçe](docs/i18n/README.tr.md),\n[Polski](docs/i18n/README.pl.md).\n\n## Why developers use it\n\n- Build AI agent social media posting into Codex, Claude Code, Cursor, OpenClaw, and custom automation tools.\n- Automate video publishing from one local file to multiple connected social accounts.\n- Give agents a safe JSON workflow: discover accounts, validate payloads, create posts, and check status.\n- Add TikTok API posting automation, Instagram Reels automation, YouTube Shorts publishing, and cross-platform social media automation without building every platform integration yourself.\n- Start free, then upgrade only when the publishing workflow grows.\n\nTaisly handles the connected accounts and posting execution. Your agent handles planning, caption writing, campaign logic, or workflow orchestration.\n\n## Free AI-first posting\n\n- Install the package for free.\n- Create or connect a Taisly account from your AI agent.\n- Let the agent authenticate, connect social accounts, validate videos, and publish through a JSON-first workflow.\n- Upgrade later when you need higher-volume publishing, larger account sets, or automatic repost workflows.\n\nNo credit card is required to get started. Paid plans are for teams and workflows that need more scale.\n\n## Agent Skill\n\nThis package includes the **Taisly Social Media Posting Skill** in `SKILL.md`. Use it with Claude Code, Codex, Cursor, OpenClaw, and other agents when you want the agent to understand the safe posting workflow before it touches live social accounts.\n\nRecommended skill workflow:\n\n```txt\nauth -> platforms -> validate -> confirm -> create -> status\n```\n\nThe skill tells agents to discover connected accounts, validate the post, ask for explicit user confirmation, create the post, and save the returned `historyId` for status checks.\n\n## Codex plugin\n\nThis package includes a Codex plugin manifest in `.codex-plugin/plugin.json`. The plugin points Codex to the canonical `SKILL.md` file and the official remote MCP server:\n\n```txt\nhttps://app.taisly.com/mcp\n```\n\nUse the plugin when you want Codex to discover both the posting workflow instructions and the Taisly MCP tools from one package. The root `SKILL.md` is the single source of truth for the agent workflow.\n\n## Install\n\n```bash\nnpm install -g @taisly/agent\n```\n\nOr run it without a global install:\n\n```bash\nnpx @taisly/agent help\n```\n\nStart the stdio MCP server:\n\n```bash\nnpx @taisly/agent mcp\n```\n\nFor local development inside this repository:\n\n```bash\nnode packages/agent/src/cli.js help\n```\n\n## Authentication\n\nThe easiest flow is to let your AI agent open the browser login for you. Use any short agent slug, for example `claude-code`, `codex`, `cursor`, `windsurf`, `openclaw`, `hermes-agent`, `cline`, or `aider`.\n\n```txt\nHelp me set up Taisly Agent Kit.\n\n1. Install the CLI: npm i -g @taisly/agent\n2. Run taisly setup --agent <agent-slug> and send me the login URL so I can finish authentication.\n3. Wait for me to finish login in the browser.\n4. Run taisly checkin --agent <agent-slug>.\n5. Tell me if Taisly is connected and ready. If not, tell me what failed.\n\nIf you cannot install or run the Taisly CLI in this environment, stop and tell me to open Taisly Settings instead.\n```\n\nThe setup command stores a local Taisly agent credential, so later CLI and MCP commands can run without manually copying an API key.\n\nManual fallback: create an API key in [Taisly Settings](https://app.taisly.com/en/settings), then set:\n\n```bash\nexport TAISLY_API_KEY=\"taisly_...\"\n```\n\nAdvanced: by default, the browser setup stores the local credential in `~/.taisly/config.json`. Most users should not change this. Set `TAISLY_CONFIG_HOME=/path/to/dir` only for CI, tests, or isolated agent profiles that need a separate credential store.\n\n## Quick start\n\nList the connected social accounts available to the API key:\n\n```bash\ntaisly auth:status\ntaisly platforms:list\n```\n\nConnect a social account from an AI-agent flow:\n\n```bash\ntaisly platforms:connect:start --platform instagram\n# Open the returned connectUrl and finish authorization in the browser.\ntaisly platforms:connect:check --platform instagram\ntaisly platforms:list\n```\n\nSupported connect slugs: `instagram`, `tiktok`, `youtube`, `x`, `facebook`.\n\nValidate a local video before publishing:\n\n```bash\ntaisly posts:validate \\\n  --video ./launch.mp4 \\\n  --platforms platform_id_1,platform_id_2 \\\n  --description \"Launch day\"\n```\n\nPublish now:\n\n```bash\ntaisly posts:create \\\n  --video ./launch.mp4 \\\n  --platforms platform_id_1,platform_id_2 \\\n  --description \"Launch day\"\n```\n\nSchedule for later:\n\n```bash\ntaisly posts:create \\\n  --video ./launch.mp4 \\\n  --platforms platform_id_1,platform_id_2 \\\n  --description \"Launch day\" \\\n  --scheduled \"2026-06-14T09:00:00+07:00\"\n```\n\nCheck the returned post:\n\n```bash\ntaisly posts:status --id <historyId>\n```\n\nEvery command prints JSON so agents can parse results without scraping terminal text.\n\n## MCP server\n\nTaisly is published in the official MCP Registry as:\n\n```txt\nio.github.taisly/agent\n```\n\nDisplay name: **Taisly Social Media Posting**\n\nRemote MCP endpoint:\n\n```txt\nhttps://app.taisly.com/mcp\n```\n\nThe remote MCP server uses streamable HTTP and OAuth. Remote MCP tools can publish only from public `videoUrl` values because they cannot read local files from your machine.\n\nCodex remote MCP setup:\n\n```bash\ncodex mcp add taisly --url https://app.taisly.com/mcp\ncodex mcp login taisly\n```\n\nClaude Code remote MCP setup:\n\n```bash\nclaude mcp add --transport http taisly https://app.taisly.com/mcp\n```\n\nThen ask Claude Code to verify the connection. If OAuth is needed, Claude Code can guide the browser login from the session. You can also authenticate explicitly with `claude mcp login taisly` if you want to complete the OAuth flow from the shell before using tools.\n\nTaisly Agent Kit also includes a local stdio MCP server in the same package. Use local MCP when your agent needs to read local video files:\n\n```json\n{\n  \"mcpServers\": {\n    \"taisly\": {\n      \"command\": \"npx\",\n      \"args\": [\"@taisly/agent\", \"mcp\"]\n    }\n  }\n}\n```\n\nIf you already use a manual API key, you can still pass `TAISLY_API_KEY` in the MCP server `env` block.\n\nCodex local MCP setup:\n\n```bash\ncodex mcp add taisly -- npx @taisly/agent mcp\n```\n\nClaude Code local MCP setup:\n\n```bash\nclaude mcp add taisly -- npx @taisly/agent mcp\n```\n\nThen ask the agent:\n\n```txt\nUse the local Taisly MCP server you just added and run the Taisly agent setup start tool with agentId: \"<agent-slug>\".\n\nSend me the login URL and wait for me to finish in the browser.\nThen run the Taisly agent checkin tool with agentId: \"<agent-slug>\".\nAfter checkin, run the Taisly auth status tool.\nTell me if Taisly is connected and ready. If not, tell me what failed.\n```\n\nAvailable MCP tools:\n\n- `taisly_agent_setup_start`\n- `taisly_agent_checkin`\n- `taisly_auth_status`\n- `taisly_platforms_list`\n- `taisly_platform_schema`\n- `taisly_platform_connect_start`\n- `taisly_platform_connect_check`\n- `taisly_posts_validate`\n- `taisly_posts_create`\n- `taisly_posts_status`\n- `taisly_posts_list`\n- `taisly_reposts_list`\n- `taisly_reposts_create`\n\n`taisly_posts_create` requires `confirmed: true`. Set it only after the user explicitly approves the video, destination accounts, caption, and schedule.\n\n## JSON workflow for agents\n\nAgents can write a payload file and pass it to the CLI:\n\n```json\n{\n  \"video\": \"./launch.mp4\",\n  \"platforms\": [\"platform_id_1\", \"platform_id_2\"],\n  \"description\": \"Launch day. Short demo, big update.\",\n  \"scheduled\": \"2026-06-14T09:00:00+07:00\"\n}\n```\n\nThen run:\n\n```bash\ntaisly posts:validate --json ./campaign.json\ntaisly posts:create --json ./campaign.json\n```\n\nThe `video` path must point to a real local file available to the agent. Supported local preflight extensions are `.mp4`, `.mov`, `.avi`, `.mkv`, `.webm`, `.flv`, `.mpeg`, and `.mpg`.\n\n## Commands\n\n```bash\ntaisly auth:status\ntaisly setup --agent <agent-slug>\ntaisly checkin --agent <agent-slug>\ntaisly platforms:list\ntaisly integrations:list\ntaisly platforms:schema --platform TikTok\ntaisly posts:validate --video ./launch.mp4 --platforms platform_id_1 --description \"Launch day\"\ntaisly posts:create --video ./launch.mp4 --platforms platform_id_1 --description \"Launch day\"\ntaisly posts:create --json ./campaign.json\ntaisly posts:list --page 1\ntaisly posts:status --id <historyId>\ntaisly reposts:list\ntaisly reposts:create --from <platform_id> --to <platform_id_1,platform_id_2>\ntaisly mcp\n```\n\n`integrations:*` commands are aliases for `platforms:*` commands. Taisly calls connected social accounts platforms in the app, while many public APIs call them integrations.\n\n## SDK\n\n```js\nimport { Taisly } from \"@taisly/agent\";\n\nconst taisly = new Taisly({\n  apiKey: process.env.TAISLY_API_KEY,\n});\n\nconst platforms = await taisly.platforms.list();\n\nconst validation = await taisly.posts.validate({\n  video: \"./launch.mp4\",\n  platforms: [platforms.data[0].id],\n  description: \"Launch day\",\n});\n\nconst post = await taisly.posts.create({\n  video: \"./launch.mp4\",\n  platforms: [platforms.data[0].id],\n  description: \"Launch day\",\n  scheduled: \"2026-06-14T09:00:00+07:00\",\n});\n\nconsole.log(validation.success);\nconsole.log(post.historyId);\n```\n\n## Use with AI agents\n\nTaisly Agent Kit is designed for agentic workflows where the user gives a high-level instruction and the agent executes a safe posting path.\n\n- Codex: let a coding agent publish demo videos, launch clips, or build updates after user confirmation.\n- Claude Code: add social posting to local content workflows and campaign scripts.\n- Cursor: ship video publishing from developer tools, content apps, and internal automation.\n- OpenClaw and other agents: connect planning, caption writing, and posting execution through a single CLI.\n\nRecommended agent path:\n\n```txt\nauth:status -> platforms:list -> platforms:schema -> posts:validate -> user confirmation -> posts:create -> posts:status\n```\n\n## Agent recipes\n\nThe `examples/` folder includes copy-paste workflows for common coding agents:\n\n- `examples/codex/post-video.md`\n- `examples/claude-code/schedule-video.md`\n- `examples/cursor/post-build-demo-video.md`\n- `examples/post-video.sh`\n- `examples/schedule-video.sh`\n\n## What this package is not\n\n- It is not a social media dashboard.\n- It is not a video editor.\n- It does not replace a Taisly account.\n- It requires connected social accounts and a Taisly agent credential or API key.\n- It does not bypass platform rules, account permissions, or media validation.\n\n## Current limits\n\n- `posts:create` uses the existing multipart `/post` API.\n- `posts:status` reads recent history because a single-post status endpoint is not available yet.\n- `posts:validate` is local preflight; final validation still happens in Taisly.\n- Local MCP uses stdio transport. Remote MCP uses streamable HTTP at `https://app.taisly.com/mcp`.\n- Remote MCP requires public video URLs; use local MCP or the CLI for local video files.\n- Media upload reuse is planned later.\n\n## Links\n\n- Taisly: <https://taisly.com/en>\n- Agent Kit page: <https://taisly.com/en/ai-agent-kit>\n- API docs: <https://docs.taisly.com/en/docs>\n- npm package: <https://www.npmjs.com/package/@taisly/agent>\n- GitHub repo: <https://github.com/taisly/agent>\n- MCP Registry: <https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.taisly%2Fagent>\n- SEO guide: <https://taisly.com/en/blog/ai-agent-social-media-posting-api>\n",
  "bytes": 13381,
  "sha": "b810cf86b413a332f5f101ef5ebb5273dd8bebcf0a3032f60e30d899f97d414d",
  "repo_slug": "taisly/agent",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_taisly_agent_1f708af8/readme"
}