mcpField
C
Chat33

Chat33

Remote
chat33.ioSocial Media0Updated 2d ago

About Chat33

Chat33 is a hosted social media MCP server for AI agents and MCP clients. It combines publishing and scheduling across eight networks with inbox and comment replies, analytics, and draft-based automation flows.

Key features

  1. 01Publish and schedule social posts
  2. 02Reply to Instagram and Facebook messages
  3. 03Manage comments and comment-to-DM flows
  4. 04Upload media and review analytics
  5. 05Handle approvals and post records

Use cases

  1. 01Schedule content across connected networks
  2. 02Review incoming messages and prepare replies
  3. 03Create a comment-triggered direct-message flow

MCP support

The hosted Streamable HTTP server exposes Chat33 tools for accounts, publishing, media, analytics, automations, inbox conversations, and comments. Clients authenticate through browser-based OAuth 2.1 or an API key.

Configuration

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

Endpointhttps://chat33.io/api/mcp/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

Details

From the project README

Chat33

Chat33 MCP Server

Social media MCP server for AI agents. Connect Claude, ChatGPT, Cursor, VS Code or any MCP client to Chat33 and let your agent publish and schedule posts to Instagram, Facebook, Threads, TikTok, YouTube, X, LinkedIn and Bluesky, answer Instagram and Facebook DMs and comments, and build comment-to-DM automations.

This is a hosted (remote) server. There is nothing to install or run: point your client at the URL below and sign in.

https://chat33.io/api/mcp/mcp
  • Transport: Streamable HTTP
  • Auth: OAuth 2.1 sign-in in the browser (dynamic client registration), or an API key header
  • Docs: chat33.io/mcp

Connect your client

Prefer OAuth wherever your client supports it: add the server, choose Authenticate (or the client's login button) and approve in the browser tab that opens. No API key needed.

Claude Code
claude mcp add --transport http --scope user chat33 https://chat33.io/api/mcp/mcp

Then run /mcp, choose chat33 → Authenticate and approve in the browser.

Claude (claude.ai and Claude Desktop)

Settings → Connectors → Add custom connector → URL https://chat33.io/api/mcp/mcp → Connect, then approve in the browser.

ChatGPT

Settings → Apps / Connectors → Advanced → turn on Developer mode → Create: name Chat33, URL https://chat33.io/api/mcp/mcp, authentication OAuth. Sign in to Chat33 and click Allow.

Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "chat33": {
      "url": "https://chat33.io/api/mcp/mcp"
    }
  }
}
VS Code

.vscode/mcp.json in your workspace (or the user MCP config):

{
  "servers": {
    "chat33": {
      "type": "http",
      "url": "https://chat33.io/api/mcp/mcp"
    }
  }
}
Windsurf

~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "chat33": {
      "serverUrl": "https://chat33.io/api/mcp/mcp"
    }
  }
}
Codex
codex mcp add chat33 --url https://chat33.io/api/mcp/mcp
codex mcp login chat33
Gemini CLI
gemini extensions install https://github.com/chat33-io/chat33-mcp
Clients without OAuth (API key)

Create a key in Chat33 → Settings → API Keys and send it as an x-api-key header (or Authorization: Bearer):

{
  "mcpServers": {
    "chat33": {
      "url": "https://chat33.io/api/mcp/mcp",
      "headers": { "x-api-key": "sk_live_..." }
    }
  }
}

Tools

GroupTools
Accountlist_accounts, whoami
Publishingcreate_post, validate_post, list_posts, get_post, delete_post, get_post_logs, request_approval, list_approvals, add_post_note
Mediaupload_media, create_upload_url
Analyticsget_analytics
Automationslist_flows, get_flow, create_flow, set_flow_status
Inboxlist_conversations, get_messages, reply_to_conversation
Commentslist_post_comments, reply_to_comment

Tools that message a real person (reply_to_conversation, reply_to_comment) tell the agent to ask for your approval first. New automations are created as drafts.

Try asking

  • "Schedule this photo to Instagram and Threads for tomorrow at 9am."
  • "Which DMs are waiting for a reply? Draft answers for me to approve."
  • "Build a flow that DMs the guide link to anyone who comments GUIDE on my last reel."
  • "How did my posts do this week?"

Limits

  • Your Chat33 plan's limits on posts and connected accounts apply.
  • Instagram and Facebook DM replies only work within 24 hours of the contact's last message.
  • Meta allows one private reply per comment, within 7 days.
  • LinkedIn: personal profiles only. Bluesky: publishing only (no DMs or comments).

Links

License

MIT. This repository describes the hosted server; the server itself runs at chat33.io.

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.