MCP server for findsaunaplunge.com — US cold plunge & sauna venues with dated, source-quoted temperatures and prices. Remote Streamable HTTP at https://findsaunaplunge.com/mcp
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
git clone https://github.com/findsaunaplunge/mcp{
"mcpServers": {
"mcp": {
"command": "node",
"args": ["/path/to/mcp/dist/index.js"]
}
}
}Resumen de MCP Servers
# FindSaunaPlunge MCP server
Model Context Protocol server for [findsaunaplunge.com](https://findsaunaplunge.com): cold plunge, sauna and contrast-therapy venues across 23 US metros (548 venues, August 2026). Every published temperature and price is read from the venue's own pages and carries its source URL, capture date and verbatim quote. **Absent fields mean the venue does not publish that detail — never zero.**
- **Endpoint:** `https://findsaunaplunge.com/mcp` — Streamable HTTP, stateless, no auth, open CORS. `GET` serves human documentation; `POST` is JSON-RPC.
- **Registry:** [`com.findsaunaplunge/findsaunaplunge`](https://registry.modelcontextprotocol.io) (domain-verified).
- **Data:** same records as the CC BY 4.0 feed [`/api/v1/venues.json`](https://findsaunaplunge.com/api/v1/venues.json); archived monthly at [github.com/findsaunaplunge/data](https://github.com/findsaunaplunge/data), DOI [10.5281/zenodo.22132913](https://doi.org/10.5281/zenodo.22132913).
## Tools
| Tool | Arguments | Returns |
| --- | --- | --- |
| `search_venues` | `query?`, `citySlug?`, `modality?`, `access?`, `maxDropInUsd?`, `limit?` | Compact venue records; filters AND-combine. `maxDropInUsd` matches only venues with a **published** drop-in price. |
| `get_venue` | `id` | The full feed record, including per-fact `sources`. |
| `list_cities` | — | Covered cities with venue counts and available modalities. |
| `get_city_stats` | `citySlug` | Counts, published price and temperature ranges, contrast-capable venues. |
| `get_data_freshness` | — | When the feed was built and the newest/oldest `lastVerified`. |
## Connect
```bash
# Claude Code
claude mcp add --transport http findsaunaplunge https://findsaunaplunge.com/mcp
# Any client, by hand
curl -s -X POST https://findsaunaplunge.com/mcp -H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_venues","arguments":{"citySlug":"austin-tx","modality":"cold_plunge","limit":3}}}'
```
## Run it yourself
The handler needs nothing but the public feed, so it runs anywhere with Node 24+:
```bash
node src/serve.ts # Streamable HTTP on :8080 — POST /mcp
node src/serve.ts --stdio # JSON-RPC over stdio, one message per line
docker build -t findsaunaplunge-mcp . && docker run -i findsaunaplunge-mcp # stdio
```
Both modes read `https://findsaunaplunge.com/api/v1/venues.json` (override with `FINDSAUNAPLUNGE_ORIGIN`), so a self-hosted copy serves exactly what the site serves.
## How it runs
`src/mcp.ts` is the whole server: one `handleMcp(request, env)` function mounted at `/mcp` inside the site's Cloudflare Worker. It has no dependencies. Tool results come from the static `/api/v1/venues.json` asset produced by the site build (fetched through the Worker's `ASSETS` binding and memoized per isolate), so the server can never disagree with the site and a deploy refreshes it automatically. `server.json` is the registry manifest.
This repository is the published source of that server. The site itself is not open source.
## Design rules
- Stateless: no sessions, no server-initiated SSE. Every `POST` is self-contained.
- Unknown arguments are rejected with a message naming the valid ones, rather than silently ignored.
- Nothing here is, or will be, a paid placement.
## Licence
MIT — see [LICENSE](LICENSE). The venue data the server serves is separately licensed CC BY 4.0.
Lo que la gente pregunta sobre mcp
¿Qué es findsaunaplunge/mcp?
+
findsaunaplunge/mcp es mcp servers para el ecosistema de Claude AI. MCP server for findsaunaplunge.com — US cold plunge & sauna venues with dated, source-quoted temperatures and prices. Remote Streamable HTTP at https://findsaunaplunge.com/mcp Tiene 0 estrellas en GitHub y su última actualización registrada es del 2026-08-27.
¿Cómo se instala mcp?
+
Puedes instalar mcp clonando el repositorio (https://github.com/findsaunaplunge/mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar findsaunaplunge/mcp?
+
Nuestro agente de seguridad ha analizado findsaunaplunge/mcp y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene findsaunaplunge/mcp?
+
findsaunaplunge/mcp es mantenido por findsaunaplunge. La última actividad registrada en GitHub es del 2026-08-27, con 0 issues abiertos.
¿Hay alternativas a mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/findsaunaplunge-mcp)<a href="https://claudewave.com/repo/findsaunaplunge-mcp"><img src="https://claudewave.com/api/badge/findsaunaplunge-mcp" alt="Featured on ClaudeWave: findsaunaplunge/mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!