MCP Server

Schedule & Chill ships a native Model Context Protocol server, so AI tools — Claude Code, Claude Desktop, Cursor, Gemini CLI, or your own agent — can schedule posts, upload video from your machine, and read your queue as first-class tools. No glue code: the agent calls tools directly.

Endpoint

https://schedulenchill.com/mcp

Authentication

The MCP server uses the same API keys as the REST API. Send your key as a bearer token:

Authorization: Bearer YOUR_API_KEY

Create a key under Settings → API Keys (see Authentication).

What it exposes

Kind	Items
Tools	schedule_post, update_post, get_post, list_scheduled, cancel_post, get_accounts, get_groups, browse_media, upload_media, get_stats
Resources	Connected Accounts, Upcoming Schedule, Media Library, Get Started
Prompts	content_idea, draft_post

Connecting

Connect Your AI Tool has copy-paste setup for Claude Code, Claude Desktop, Cursor, VS Code, Gemini CLI, Codex, Windsurf, Zed, Kimi CLI, OpenClaw, Hermes, and any other MCP client.

The short version — Claude Code, one command:

claude mcp add --transport http schedulenchill https://schedulenchill.com/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Clients that speak stdio only (Claude Desktop, Codex, Zed) need the mcp-remote bridge rather than a plain URL — the setup guide covers each one.

ChatGPT connectors are not supported yet. They authenticate with OAuth and offer no field for a static bearer header, so pointing one at this endpoint fails auth. Use the REST API from ChatGPT instead. OAuth support is on the roadmap.

A typical agent flow

1. Call get_accounts to discover where it can post.
2. Optionally browse_media (or upload_media from a URL) to attach visuals.
3. Call schedule_post with content, platforms, and an optional time.
4. Confirm with list_scheduled, or cancel_post to undo.

See Tools for full parameters.