# arr-mcp
### Talk to your entire media stack. One server, one endpoint, one conversation.
**Radarr ยท Sonarr ยท Prowlarr ยท Bazarr ยท Jellyfin ยท Plex ยท Seerr ยท SABnzbd ยท Transmission ยท qBittorrent**
[](https://github.com/bardesss/arr-mcp/releases)
[](https://github.com/bardesss/arr-mcp/actions)
[](https://github.com/bardesss/arr-mcp/pkgs/container/arr-mcp)
[](https://github.com/bardesss/arr-mcp/pkgs/container/arr-mcp)
[](LICENSE)
## Everyone else ships one MCP server per service. This is one for the stack.
That difference is the whole point, because the interesting questions live
*between* services:
> *"Why isn't the film I requested on Tuesday showing up in Jellyfin?"*
No single service can answer that. It spans Seerr, Radarr, Prowlarr, SABnzbd and
Jellyfin โ five APIs, five sets of ids, five half-answers. arr-mcp correlates
them and hands back the causal chain:
```
diagnose { query: "Blade" }
```
> No file on disk yet. Trigger a search in Radarr or Sonarr โ nothing is
> downloading and no indexer reported a failure.
One call. One answer. It even answers with a service down, and tells you which
part it could not check rather than guessing across the hole.
## Why people run it
| | |
| --- | --- |
| ๐ **`diagnose` answers what no single service can** | Walks the whole chain โ requested, managed, monitored, downloaded, indexed, imported, scanned โ and names the *first* thing that explains the absence. |
| ๐ก๏ธ **Indexer text is data, never instruction** | Release names from public indexers are attacker-controllable and flow straight into model context. arr-mcp fences every one of them. |
| โ **Writes are opt-in, previewed, recorded** | Off until you turn them on, per service. Every write shows you exactly what it would do and waits for confirmation โ and lands in an audit trail either way. |
| ๐ฅ๏ธ **A config page that diagnoses** | Add services from a browser, see what is broken *and what to do about it*, read the logs and the write audit. No YAML required. |
| ๐ **Thirty-six tools, one vocabulary** | Every list pages the same way, every error names the config key that would fix it, every write takes ids rather than titles. |
Nothing else in this space does the last four at all.
## Quick start โ about two minutes
Also in the repo as [`docker-compose.example.yml`](https://github.com/bardesss/arr-mcp/blob/HEAD/docker-compose.example.yml).
**On Unraid**, use [`unraid/arr-mcp.xml`](https://github.com/bardesss/arr-mcp/blob/HEAD/unraid/arr-mcp.xml) instead โ a
Community Applications template with the appdata path and `99:100` ownership
already set. It is not listed in CA yet, so for now drop it into
`/boot/config/plugins/dockerMan/templates-user/` and pick it from the template
list under **Add Container**. Steps 1 to 3 below are the same once it starts.
```yaml
services:
arr-mcp:
image: ghcr.io/bardesss/arr-mcp:latest
container_name: arr-mcp
ports:
- 6060:6060
volumes:
- ./config:/config
environment:
- PUID=1000
- PGID=1000
- TZ=Europe/Amsterdam
restart: unless-stopped
```
**1. Open `http://