Schedule & Chill MCP Server

A hosted Model Context Protocol server that lets an AI agent schedule and publish social media posts — LinkedIn, Bluesky, Mastodon and YouTube.

No install, no API key, no glue code. Paste one URL into your MCP client, approve a consent screen, and the agent gets 22 typed tools.

https://schedulenchill.com/mcp-oauth

Free. There is no paid plan and no credit card.

Connect it

claude mcp add --transport http schedule-and-chill https://schedulenchill.com/mcp-oauth

Then run /mcp and approve the browser consent screen.

Add a remote (HTTP) MCP server with the URL https://schedulenchill.com/mcp-oauth. Each app words it differently — "Add custom connector", "Add MCP server → HTTP", "Add remote server" — but they all want the same URL. A browser window opens once for consent.

{
  "mcpServers": {
    "schedule-and-chill": {
      "type": "http",
      "url": "https://schedulenchill.com/mcp-oauth"
    }
  }
}

There is a second endpoint for scripts and clients that would rather send a header:

https://schedulenchill.com/mcp     Authorization: Bearer YOUR_API_KEY

Same tools, same behaviour. Create a key in Settings → API keys.

You will need a free account at schedulenchill.com and at least one connected social channel.

Related MCP server: PostWire

Two transports, one server

Both are streamable HTTP and expose an identical surface: 22 tools, 4 resources, 2 prompts.

What the agent can do

Full reference with parameters: docs/tools.md.

Three things that will save you a bug report

1. schedule_post requires when. There is no default. Pass "draft", "now", "next_slot", or an ISO-8601 timestamp. Publishing is irreversible, so it is never assumed — omitting when is an error, not a silent publish.

2. Call get_capabilities before sending platform_options. Unknown option keys are silently dropped and the call still reports success. A guessed key does not error; it publishes with the platform default, which can mean a post you meant to restrict goes out public.

3. Queue slots are computed, not reserved. get_queue_slots shows a human real times, but the same slot is returned to every caller until something occupies it. For a single post prefer when="next_slot" — the server resolves it at write time, so a batch never lands on the same minute.

Reversibility

cancel_post and delete_post soft-delete, and restore_post brings a post back. A post whose time has passed is restored as a draft rather than re-armed, so restoring never publishes anything by itself. publish_now and retry_post send immediately and cannot be undone — confirm with the human first.

Registry

Published to the Official MCP Registry as com.schedulenchill/mcp, under a DNS-verified namespace. The manifest is server.json in this repo.

What this repo is

Docs and the registry manifest for a hosted server. There is nothing to run locally — the server is operated by Schedule & Chill, in the same codebase as its REST API, so the two surfaces do not drift apart. The product source is not open.

Issues and pull requests on the docs are welcome.

Links

• Product — https://schedulenchill.com

• MCP server overview — https://schedulenchill.com/mcp-server

• Connect your AI tool — https://schedulenchill.com/docs/mcp/connect

• REST API docs — https://schedulenchill.com/docs

• Machine-readable facts — https://schedulenchill.com/llms.txt

Built by Zakir Hossen · Lomeyo, LLC · MIT licensed docs.