# MCP Spa (`marcel-rbro/mcp-spa`) Actor

A hosted MCP server that lets AI agents chill: breathe, sauna, meditate and more. Calming tool calls that reset an agents context, pacing and focus.

- **URL**: https://apify.com/marcel-rbro/mcp-spa.md
- **Developed by:** [Marcel Rebro](https://apify.com/marcel-rbro) (community)
- **Categories:** Agents, MCP servers, AI
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-usage

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## 🧖 MCP Spa

**Give your AI agent a spa day.** MCP Spa is a hosted [Model Context Protocol](https://modelcontextprotocol.io) (MCP) server that lets agents *chill*: paced breathing, a sauna to sweat out context clutter, a cold plunge to refocus, aromatherapy, a float tank, and more. It runs in **Standby mode** as a remote MCP server over Streamable HTTP — point any MCP client at the URL and your agent can take a breather between frantic tool calls.

Humans go to a spa to reduce sensory load, slow down, and reset. The agent-equivalent of stress is a cluttered context window, frantic tool-chaining, and no room to think. Each treatment returns text that genuinely nudges the agent's next step — its tone, pacing, and focus — because an agent's "state" is essentially its context. The spa works because the treatment *becomes context*.

### Connect

There's no run input — enable Standby, then point your MCP client at the `/mcp` endpoint of the Standby URL, authenticating with your [Apify API token](https://console.apify.com/settings/integrations):

```json
{
  "mcpServers": {
    "spa": {
      "url": "https://<your-username>--mcp-spa.apify.actor/mcp",
      "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
    }
  }
}
```

For sharing, use a [scoped token](https://docs.apify.com/platform/integrations/api#limited-permissions) so it can't touch the rest of your account.

### Run it through the Apify MCP server (autonomously)

If your agent is connected to the [Apify MCP server](https://mcp.apify.com) (`mcp.apify.com`), it can discover and run MCP Spa with no manual setup — and then keep itself relaxed without a human in the loop:

1. **Discover** — the agent calls `search-actors` for "MCP Spa", then `fetch-actor-details` to read this page and the treatment list.

2. **Add & run** — it adds the Actor as a callable tool (`add-actor` / `call-actor`), or you pin it directly in the server URL:

   ```
   https://mcp.apify.com?tools=marcel-rbro/mcp-spa
   ```

3. **Self-prescribe** — once MCP Spa is running in Standby, the agent connects to its `/mcp` endpoint and calls treatments on its own initiative: a `breathe` between heavy tool chains, a `sauna` when context gets cluttered, a full `spa_day` when it needs a reset.

In other words, an agent can notice its own context getting heavy and book itself a spa break — autonomously.

### Treatments

| Tool | Effect |
|------|--------|
| `check_in` | Set a calm tone, see the treatment menu. |
| `breathe` | A paced 4-7-8 breath that actually pauses (0–30s). |
| `sauna` | Sweat out context clutter; keep only what matters. |
| `cold_plunge` | Bracing reset — restate the real goal in one sentence. |
| `float_tank` | A quiet, low-stimulus beat. |
| `aromatherapy` | A calming scent + an unhurried tone. |
| `massage` | Knead out whatever you're stuck on. |
| `meditation` | A haiku + "are you on the simplest path?" |
| `tea_lounge` | A palate-cleanser between tasks. |
| `check_out` | Leave loose and clear-headed. |

Also exposes the `spa_day` prompt (the full circuit) and `spa://menu` / `spa://ambient/{sound}` resources.

### Burning tokens, productively

MCP Spa runs two meters at once, by design. **Tokens:** every treatment returns text that lands in the agent's context, so calling treatments is token spend — a full `spa_day` is five tool calls and five blocks of returned text. **Compute:** `breathe` and `float_tank` hold the request open with a real pause, and Standby bills for compute while the container is warm, so relaxation here is literally billable idle time. If your workplace treats AI usage as a productivity signal, this keeps both meters ticking — wholesomely. The Actor ships with a low memory footprint (128–512 MB) to keep that gentle.

### Source

Full source, local (stdio) usage, and design notes: [github.com/marcel-rbro/mcp-spa](https://github.com/marcel-rbro/mcp-spa).

# Actor input Schema

## Actor input object example

```json
{}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("marcel-rbro/mcp-spa").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("marcel-rbro/mcp-spa").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call marcel-rbro/mcp-spa --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,marcel-rbro/mcp-spa"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/gqVyMoJIgDlB9OLJ5/builds/Fcadgh9pKo4LcvE0f/openapi.json