{
  "markdown": "# Schedule & Chill MCP Server\n\nA hosted [Model Context Protocol](https://modelcontextprotocol.io) server that lets an AI\nagent schedule and publish social media posts — **LinkedIn, Bluesky, Mastodon and YouTube**.\n\nNo install, no API key, no glue code. Paste one URL into your MCP client, approve a consent\nscreen, and the agent gets 22 typed tools.\n\n```\nhttps://schedulenchill.com/mcp-oauth\n```\n\n**Free.** There is no paid plan and no credit card.\n\n---\n\n## Connect it\n\n<details open>\n<summary><b>Claude Code</b></summary>\n\n```bash\nclaude mcp add --transport http schedule-and-chill https://schedulenchill.com/mcp-oauth\n```\nThen run `/mcp` and approve the browser consent screen.\n</details>\n\n<details>\n<summary><b>Claude Desktop / ChatGPT / Cursor / VS Code / Zed</b></summary>\n\nAdd a remote (HTTP) MCP server with the URL `https://schedulenchill.com/mcp-oauth`.\nEach app words it differently — \"Add custom connector\", \"Add MCP server → HTTP\", \"Add\nremote server\" — but they all want the same URL. A browser window opens once for consent.\n</details>\n\n<details>\n<summary><b>Anything that only takes a config file</b></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"schedule-and-chill\": {\n      \"type\": \"http\",\n      \"url\": \"https://schedulenchill.com/mcp-oauth\"\n    }\n  }\n}\n```\n</details>\n\n<details>\n<summary><b>API key instead of OAuth</b></summary>\n\nThere is a second endpoint for scripts and clients that would rather send a header:\n\n```\nhttps://schedulenchill.com/mcp     Authorization: Bearer YOUR_API_KEY\n```\n\nSame tools, same behaviour. Create a key in Settings → API keys.\n</details>\n\nYou will need a free account at [schedulenchill.com](https://schedulenchill.com) and at\nleast one connected social channel.\n\n---\n\n## Two transports, one server\n\n| Endpoint | Auth | Use it when |\n|---|---|---|\n| `/mcp-oauth` | OAuth 2.1 + PKCE, dynamic client registration | Almost always. Nothing to copy or store, and each client is revocable on its own. |\n| `/mcp` | Static bearer token | Scripts, CI, anything without a browser. |\n\nBoth are streamable HTTP and expose an identical surface: **22 tools, 4 resources, 2 prompts**.\n\n---\n\n## What the agent can do\n\nFull reference with parameters: **[docs/tools.md](docs/tools.md)**.\n\n| Area | Tools |\n|---|---|\n| Write & schedule | `schedule_post` · `update_post` · `duplicate_post` |\n| Read the queue | `list_posts` · `get_post` · `get_queue_slots` |\n| Publish & recover | `publish_now` · `retry_post` · `cancel_post` · `delete_post` · `restore_post` |\n| Accounts & limits | `get_accounts` · `get_groups` · `get_capabilities` · `get_tiktok_creator_info` |\n| Media library | `browse_media` · `upload_media` · `update_media` · `list_asset_vocabulary` |\n| Measurement | `get_stats` · `get_analytics` |\n\n### Three things that will save you a bug report\n\n1. **`schedule_post` requires `when`.** There is no default. Pass `\"draft\"`, `\"now\"`,\n   `\"next_slot\"`, or an ISO-8601 timestamp. Publishing is irreversible, so it is never\n   assumed — omitting `when` is an error, not a silent publish.\n2. **Call `get_capabilities` before sending `platform_options`.** Unknown option keys are\n   silently dropped and the call still reports success. A guessed key does not error; it\n   publishes with the platform default, which can mean a post you meant to restrict goes\n   out public.\n3. **Queue slots are computed, not reserved.** `get_queue_slots` shows a human real times,\n   but the same slot is returned to every caller until something occupies it. For a single\n   post prefer `when=\"next_slot\"` — the server resolves it at write time, so a batch never\n   lands on the same minute.\n\n### Reversibility\n\n`cancel_post` and `delete_post` soft-delete, and `restore_post` brings a post back. A post\nwhose time has passed is restored as a draft rather than re-armed, so restoring never\npublishes anything by itself. `publish_now` and `retry_post` send immediately and cannot be\nundone — confirm with the human first.\n\n---\n\n## Registry\n\nPublished to the [Official MCP Registry](https://registry.modelcontextprotocol.io) as\n`com.schedulenchill/mcp`, under a DNS-verified namespace. The manifest is\n[`server.json`](server.json) in this repo.\n\n---\n\n## What this repo is\n\nDocs and the registry manifest for a **hosted** server. There is nothing to run locally —\nthe server is operated by Schedule & Chill, in the same codebase as its REST API, so the\ntwo surfaces do not drift apart. The product source is not open.\n\nIssues and pull requests on the docs are welcome.\n\n## Links\n\n- Product — <https://schedulenchill.com>\n- MCP server overview — <https://schedulenchill.com/mcp-server>\n- Connect your AI tool — <https://schedulenchill.com/docs/mcp/connect>\n- REST API docs — <https://schedulenchill.com/docs>\n- Machine-readable facts — <https://schedulenchill.com/llms.txt>\n\nBuilt by [Zakir Hossen](https://github.com/devzakir) · Lomeyo, LLC · MIT licensed docs.\n",
  "bytes": 4875,
  "sha": "3b6503c77dc2783d0386c10c6bdff4a93f1e51d8106769bb01de3266bc7c9926",
  "repo_slug": "lomeyollc/schedulenchill-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_schedulenchill_mcp_0d83c1d0/readme"
}