OmniSocials MCP & CLI for any AI

OmniSocials uses MCP (Model Context Protocol), an open standard that gives AI agents access to external tools. Once connected, your agent can draft, schedule, and publish posts, pull analytics, reply to your inbox, and manage ad campaigns.

OmniSocials MCP works with Claude (web, desktop, and Claude Code), ChatGPT, Cursor, OpenClaw, Hermes, Windsurf, Codex, and Gemini CLI. Any agent or client that supports MCP can connect to OmniSocials.

Your agent gets access to 49 tools across 8 categories: posts, scheduling, media, analytics, your social inbox, boosting and ads, webhooks, and workspaces. Your agent picks the right tool for the task automatically.

Posts, Stories, and Reels across 11 platforms, with per-platform captions, media up to 50MB, first comments, scheduled times, and platform-specific options like Pinterest boards or YouTube metadata. You can publish immediately or save everything as drafts.

Not for remote clients like claude.ai, where you sign in with your OmniSocials account through OAuth. Local setups like Claude Code use an API key, which you create in the OmniSocials app under Settings, then API Keys.

MCP and CLI access are included in the single OmniSocials plan at $10 per month billed annually, with a 14-day free trial. There is no extra charge for connecting AI tools.

You stay in control. Your assistant can save everything as drafts first and only publish when you tell it to, and you can review every post in the OmniSocials app before it goes live.

11 platforms: Instagram, Facebook, LinkedIn, YouTube, TikTok, X, Pinterest, Threads, Bluesky, Mastodon, and Google Business, all from one OmniSocials workspace.

Yes. Any MCP-compatible client can connect. Point it to the remote server at mcp.omnisocials.com, or run the stdio server locally with npx -y @omnisocials/mcp-server.