adaptlypost/agent

smithery badge

Give your AI agent the ability to post to Instagram, TikTok, YouTube, X, LinkedIn, Facebook, Pinterest, Threads, and Bluesky from a single command, and to read how those posts performed.

Supports: Instagram, TikTok, YouTube, X (Twitter), LinkedIn, Facebook, Pinterest, Threads, Bluesky

Install

npx skills add adaptlypost/agent

Works with Claude Code, Cursor, Windsurf, Codex, and any agent that supports skills.

Other installation methods

Manual: Copy the skills/adaptlypost/ folder into your project's skills directory.

Cursor remote rules: Point to https://raw.githubusercontent.com/adaptlypost/agent/main/skills/adaptlypost/SKILL.md

Setup

1. Create an account at adaptlypost.com
2. Connect your social media accounts
3. Create an API token at Settings > API Tokens
4. Run:

   ./scripts/adaptlypost.js setup --key adaptly_xxxxx
   

What it does

Once installed, your AI agent can:

• Post to 9 platforms simultaneously with per-platform caption overrides
• Schedule posts for any future time
• Bulk schedule up to 100 posts at once
• Check results per-platform success/failure with error details
• Retry just the failed platforms
• Draft & publish workflow — save drafts, review, publish later
• Read analytics — views, likes, comments, followers and engagement per window, per platform and per post

Example

You: Schedule a LinkedIn post for tomorrow at 9am about our new feature launch
Agent: Done. Post scheduled for tomorrow at 9:00 AM on your LinkedIn account.

Alternative: MCP

For deeper integration with Claude Desktop, Cursor, or other MCP-compatible clients, use the AdaptlyPost MCP server:

{
  "mcpServers": {
    "adaptlypost": {
      "type": "http",
      "url": "https://mcp.adaptlypost.com/mcp",
      "headers": {
        "Authorization": "Bearer adaptly_your_key"
      }
    }
  }
}

MCP setup docs

Run it locally

The server source lives in mcp-server/. Run it over stdio with Bun:

{
  "mcpServers": {
    "adaptlypost": {
      "command": "bun",
      "args": ["run", "/path/to/agent/mcp-server/src/index.ts"],
      "env": { "ADAPTLYPOST_API_TOKEN": "adaptly_your_key" }
    }
  }
}

Or with Docker:

docker build -t adaptlypost-mcp .
docker run -i -e ADAPTLYPOST_API_TOKEN=adaptly_your_key adaptlypost-mcp

Links

• AdaptlyPost
• AI Agents page
• API Tokens
• MCP Server

License

MIT