mcpField
A
AdaptlyPost

AdaptlyPost

VerifiedFeaturedRemote
adaptlypost.comCommunication0Updated today

About AdaptlyPost

AdaptlyPost is a social publishing service for agents, supporting post creation, scheduling, publishing, and performance checks across supported platforms. It offers both an agent skill and an MCP server, with workspace roles controlling permitted actions.

Key features

  1. 01Publish posts across supported platforms
  2. 02Schedule individual or bulk posts
  3. 03Save drafts and publish after review
  4. 04Repeat posts on a recurring schedule
  5. 05Read post and platform analytics
  6. 06Retry failed platform deliveries

Use cases

  1. 01Schedule social announcements for a future date
  2. 02Prepare drafts for team review
  3. 03Publish one campaign across multiple platforms
  4. 04Check engagement and retry failed posts

MCP support

AdaptlyPost provides a remote MCP server at its hosted endpoint and can also run locally over stdio with Bun or Docker. Clients use an API token, and available operations follow the token’s workspace role.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.adaptlypost.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

29

This tool takes no parameters.

Details

From the project README

AdaptlyPost Agent

smithery badge

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

Supports: Instagram, TikTok, YouTube, X (Twitter), LinkedIn, Facebook, Pinterest, Threads, Bluesky, Mastodon, Google Business Profile, Tumblr, Telegram

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 and pick its role
  4. Run:
    ./scripts/adaptlypost.js setup --key adaptly_xxxxx
    
Roles

A token is issued under a workspace role and never does more than the member who created it. Admin does everything, Editor creates, schedules and publishes, Contributor creates and edits its own drafts and uploads media but cannot schedule or publish, Viewer reads. Contributor is the safe choice for an agent that should not post on its own.

An operation outside the role answers 403 with code: permission_denied; the skill tells the agent to stop, save a draft where that applies, and ask a workspace member to publish, instead of retrying or hunting for another key.

What it does

Once installed, your AI agent can:

  • Post to 12 platforms simultaneously with per-platform caption overrides, first comments, thumbnails and image shapes
  • 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
  • Repeat a post daily, weekly, monthly or yearly, then pause, resume or stop the series
  • 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

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.