Skip to content
Back to search

arr-mcp

One MCP server for the whole self-hosted media stack: Radarr, Sonarr, Whisparr, Prowlarr, Bazarr, Jellyfin, Plex, Seerr, SABnzbd, Transmission, qBittorent and Profilarr.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/bardesss/arr-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/bardesss/arr-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/bardesss--arr-mcp/badge.svg)](/listings/bardesss--arr-mcp)

HTML

<a href="/listings/bardesss--arr-mcp"><img src="/api/listings/bardesss--arr-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Also in the repo as [`docker-compose.example.yml`](docker-compose.example.yml). **On Unraid**, use [`unraid/arr-mcp.xml`](unraid/arr-mcp.xml) instead — 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.

**On Proxmox VE**, [`proxmox/`](proxmox/) builds an unprivileged Debian LXC from source instead — no Docker anywhere. Run it on the host, not in a guest:

bash -c "$(curl -fsSL https://raw.githubusercontent.com/bardesss/arr-mcp/main/proxmox/ct/arr-mcp.sh)"

It defaults to 2 cores, 2 GB and 8 GB of disk — the memory is sized for the optional [IMDb ingest](docs/imdb.md), not for serving. `config.yaml`, the MCP tokens (hashed) and the databases live in `/config`, which an update does not touch; run `update` inside the container to rebuild it from the latest release. Re-running the command above on the host builds a second container instead. If it installs but never answers, `journalctl -u arr-mcp` is the log.

It follows the Community Scripts conventions but is not in their catalogue, and it has never been run on a real host — arm64 least of all, so the script asks rather than assuming. An install that worked is as useful to hear about as one that did not: [#265](https://github.com/bardesss/arr-mcp/issues/265). Steps 1 to 3 below are the same once it boots.

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://<host>:6060`** — the bare host, no path. Nothing to read out of the container log.

**2. Claim it.** The first page is a setup form rather than a sign-in: choose a username and a password of at least 12 characters.

> [!IMPORTANT] > Do this **before** exposing the port. Until it is claimed, whoever loads that > page first owns the instance — and it holds every service's API key.

**3. Add your services** — **Add a service**, paste its URL and API key (for Plex, its `X-Plex-Token`; for Transmission and qBittorrent, its username and password), save. It applies immediately; there is no restart. Configure only what you run. A config file that will not parse no longer takes the container down: arr-mcp serves a repair page with the error and an editor instead.

Your MCP client goes to `http://<host>:6060/mcp` with an MCP token. Create one on the config page; it is shown once, so copy it into your client straight away. Each token has its own tier and expiry, see [MCP tokens](docs/configuration.md#mcp-tokens). A client that can only be given a URL, not a header, can carry the token as `?token=` instead — see [`allow_token_in_url`](docs/configuration.md#allow_token_in_url). If you already run an identity provider, `/mcp` also accepts short-lived OAuth 2.1 access tokens, so each client gets its own credential and a scope that caps what it may do — read-only for one, writes for another, never more than `config.yaml` already permits. See [`auth.oauth`](docs/configuration.md#authoauth). Everything the UI does is still just `config.yaml`, and editing that by hand remains supported. Clients that read the [MCP Registry](https://registry.modelcontextprotocol.io) find it there as `io.github.bardesss/arr-mcp`.

**Works with whatever you point at it.** A client asking for `Accept: application/json` — or sending no `Accept` at all — gets one JSON object back with a `Content-Length`, rather than a refusal for not also naming `text/event-stream`. A client that does accept a stream still gets one. Even a refusal is JSON. So a plain `curl` works as-is, and so does a full MCP client.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 341 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="assets/logo.svg" alt="" width="64" height="64">
  3. # arr-mcp
  4. ### Talk to your entire media stack. One server, one endpoint, one conversation.
  5. **Radarr · Sonarr · Whisparr · Lidarr · Prowlarr · Bazarr · Jellyfin · Plex · Seerr · SABnzbd · NZBGet · Transmission · qBittorrent · Profilarr · Cleanuparr · Reclaimerr · Dispatcharr · Shelfmark · Grimmory**
  6. [![Release](https://img.shields.io/github/v/release/bardesss/arr-mcp?style=flat-square&color=6f42c1)](https://github.com/bardesss/arr-mcp/releases)
  7. [![CI](https://img.shields.io/github/actions/workflow/status/bardesss/arr-mcp/release.yml?branch=main&label=build&style=flat-square)](https://github.com/bardesss/arr-mcp/actions)
  8. [![Image](https://img.shields.io/badge/ghcr.io-arr--mcp-2496ed?style=flat-square&logo=docker&logoColor=white)](https://github.com/bardesss/arr-mcp/pkgs/container/arr-mcp)
  9. [![Platforms](https://img.shields.io/badge/platforms-amd64%20%C2%B7%20arm64-555?style=flat-square)](https://github.com/bardesss/arr-mcp/pkgs/container/arr-mcp)
  10. [![Licence](https://img.shields.io/badge/licence-MIT-green?style=flat-square)](LICENSE)
  11. <img src="screenshots/dashboard-dark.png" alt="The arr-mcp dashboard: tiles for services, health checks, tokens and writes, a Needs attention list, one row per service grouped by role with version, latency, write permission and status, and the MCP endpoint ready to copy" width="880">
  12. </div>
  13. ## Everyone else ships one MCP server per service. This is one for the stack.
  14. That difference is the whole point, because the interesting questions live
  15. *between* services:
  16. > *"Why isn't the film I requested on Tuesday showing up in Jellyfin?"*
  17. No single service can answer that. It spans Seerr, Radarr, Prowlarr, SABnzbd and
  18. Jellyfin. Five APIs, five sets of ids, five half-answers. arr-mcp correlates
  19. them and hands back the causal chain:
  20. ```
  21. diagnose_media { query: "Blade" }
  22. ```
  23. > No file on disk yet. Trigger a search in Radarr or Sonarr. Nothing is
  24. > downloading and no indexer reported a failure.
  25. It even answers with a service down, and tells you which part it could not
  26. check rather than guessing across the hole.
  27. ## Why people run it
  28. | | |
  29. | --- | --- |
  30. | 🔍 **`diagnose_media` answers what no single service can** | Walks the whole chain (requested, managed, monitored, downloaded, indexed, imported, scanned) and names the *first* thing that explains the absence. |
  31. | 🗂️ **A record that outlives the title** | Deleting a title deletes its history. Turn on the [library event log](docs/configuration.md#the-library-event-log) and arr-mcp keeps what Radarr, Sonarr and Lidarr report, so `get_history` and `diagnose_media` can still tell you what happened to it. |
  32. | 🧮 **Quality profiles that cannot do what they say** | A minimum score nothing can reach, a language preferred but never required, a format scored where its wider twin sits at zero. Hand-built or synced from TRaSH Guides through Profilarr, the same checks apply. The arithmetic ones are proved rather than guessed, and every fix names a change to make in Profilarr, which owns them. |
  33. | 🛡️ **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. |
  34. | ✋ **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, and lands in an audit trail either way. |
  35. | 🖥️ **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. |
  36. | 📚 **Forty-four tools, one vocabulary** | Every list pages the same way and answers readably whether or not your client reads `structuredContent`, every error names the config key that would fix it, every write takes ids rather than titles. |
  37. | 🪶 **It is careful with your context** | Nineteen services behind one server, and a four-service stack still lists 36 tools for about 20,700 tokens. Tools your stack cannot use, kinds it does not hold and sentences about services you do not run are never sent. |
  38. ## Quick start: about two minutes
  39. Also in the repo as [`docker-compose.example.yml`](docker-compose.example.yml).
  40. **On Unraid**, use [`unraid/arr-mcp.xml`](unraid/arr-mcp.xml) instead: a
  41. Community Applications template with the appdata path and `99:100` ownership
  42. already set. It is not listed in CA yet, so for now drop it into
  43. `/boot/config/plugins/dockerMan/templates-user/` and pick it from the template
  44. list under **Add Container**. Steps 1 to 3 below are the same once it starts.
  45. **On Proxmox VE**, [`proxmox/`](proxmox/) builds an unprivileged Debian LXC
  46. from source instead, no Docker anywhere. Run it on the host, not in a guest:
  47. ```bash
  48. bash -c "$(curl -fsSL https://raw.githubusercontent.com/bardesss/arr-mcp/main/proxmox/ct/arr-mcp.sh)"
  49. ```
  50. It defaults to 2 cores, 2 GB and 8 GB of disk. The memory is sized for the
  51. optional [IMDb ingest](docs/imdb.md), not for serving. `config.yaml`, the MCP
  52. tokens (hashed) and the databases live in `/config`, which an update does not touch; run
  53. `update` inside the container to rebuild it from the latest release. Re-running
  54. the command above on the host builds a second container instead. If it installs
  55. but never answers, `journalctl -u arr-mcp` is the log.
  56. It follows the Community Scripts conventions but is not in their catalogue. One
  57. tester has reported a clean install so far, and arm64 has not been tried, so the
  58. script asks rather than assuming. Either way,
  59. [open an issue](https://github.com/bardesss/arr-mcp/issues/new/choose). Steps 1
  60. to 3 below are the same once it boots.
  61. ```yaml
  62. services:
  63. arr-mcp:
  64. image: ghcr.io/bardesss/arr-mcp:latest
  65. container_name: arr-mcp
  66. ports:
  67. - 6060:6060
  68. volumes:
  69. - ./config:/config
  70. environment:
  71. - PUID=1000
  72. - PGID=1000
  73. - TZ=Europe/Amsterdam
  74. restart: unless-stopped
  75. ```
  76. **1. Open `http://<host>:6060`**: the bare host, no path. Nothing to read out
  77. of the container log.
  78. **2. Claim it.** The first page is a setup form rather than a sign-in: choose a
  79. username and a password of at least 12 characters.
  80. > [!IMPORTANT]
  81. > Do this **before** exposing the port. Until it is claimed, whoever loads that
  82. > page first owns the instance, and it holds every service's API key.
  83. **3. Add your services**: **Add a service**, paste its URL and API key (for Plex,
  84. its `X-Plex-Token`; for NZBGet, Transmission, qBittorrent and Grimmory, its username and password; a Shelfmark with no authentication needs no key), save. It applies immediately; there is
  85. no restart. Configure only what you run. **Find services**, next to it, looks
  86. for them first: this host on each service's default port, the usual container
  87. names, and, if you ask for it, a sweep of the address range around you. It
  88. fills in the service and its address, and leaves the key to you. A config file
  89. that will not parse does not take the container down: arr-mcp serves a repair
  90. page with the error and an editor instead.
  91. Your MCP client goes to `http://<host>:6060/mcp` with an MCP token. Create one on
  92. the **Access** page, which also carries that address and a ready client config to
  93. copy; the token itself is shown once, so copy it into your client straight away.
  94. Each token has its own tier and expiry, see
  95. [MCP tokens](docs/configuration.md#mcp-tokens). A client that can only be given a
  96. URL, not a header, can carry the token as `?token=` instead; see
  97. [`allow_token_in_url`](docs/configuration.md#allow_token_in_url). If you already
  98. run an identity provider, `/mcp` also accepts short-lived OAuth 2.1 access
  99. tokens, each with a scope that caps what that client may do, never more than
  100. `config.yaml` already permits. See [`auth.oauth`](docs/configuration.md#authoauth). Everything
  101. the UI does is still just `config.yaml`, and editing that by hand remains
  102. supported. Clients that read the
  103. [MCP Registry](https://registry.modelcontextprotocol.io) find it there as
  104. `io.github.bardesss/arr-mcp`. It is also listed on Glama:
  105. [![arr-mcp MCP server: quality and maintenance score on Glama](https://glama.ai/mcp/servers/bardesss/arr-mcp/badges/card.svg)](https://glama.ai/mcp/servers/bardesss/arr-mcp)
  106. A client that launches its servers as child processes can run arr-mcp
  107. [over stdio](docs/configuration.md#over-stdio) instead, with `--stdio`. That
  108. connection is read-only; writes need `/mcp` and a token.
  109. **Works with whatever you point at it.** A client asking for
  110. `Accept: application/json`, or sending no `Accept` at all, gets one JSON object
  111. back rather than a refusal for not also naming `text/event-stream`. A client
  112. that accepts a stream still gets one. Even a refusal is JSON, so a plain `curl`
  113. works as-is.
  114. Image tags are `X.Y.Z`, `X.Y`, `X` and `latest`, plus `main` for bleeding edge.
  115. Pin a major (`:2`) and no tool or parameter you rely on goes away; pin a minor
  116. (`:2.0`) if you would rather approve each new tool surface yourself. Images are published for **amd64 and arm64**, so a Raspberry Pi or an
  117. ARM NAS runs the same build as everything else.
  118. ## What you can ask it
  119. Forty-four tools, but you never name them. You ask, and the model picks:
  120. > *"What's downloading right now, and is anything stuck?"*
  121. > *"What aired this week that I haven't watched?"*
  122. > *"Which of my indexers are failing, and what did they say?"*
  123. > *"Find me something highly rated from 1994 I don't already have."*
  124. > *"Go and find Dutch subtitles for the film that just landed."*
  125. > *"Not that release, grab the 1080p remux instead."*
  126. > *"Why does this episode keep failing and never downloading?"*
  127. > *"Pause SABnzbd, I need the bandwidth for an hour."*
  128. > *"What are my seeding rules, and is anything still seeding past them?"*
  129. > *"That download finished days ago and never got imported. Sort it out."*
  130. > *"Put this series on the 4K profile and only monitor future seasons."*
  131. > *"This profile says it wants Dutch but keeps grabbing English, why?"*
  132. > *"Has anything in Radarr drifted from what Profilarr set?"*
  133. > *"Why is the TV guide empty, and is my IPTV subscription about to run out?"*
  134. > *"Did that book ever get imported, or is it still waiting in the Bookdrop?"*
  135. > *"Which of my shows have metadata that does not match the files?"*
  136. > *"These episode titles are wrong for the files. Fix them."*
  137. > *"Unmonitor season 5 and delete its files."* Previewed first, always.
  138. ## Poster cards in Claude
  139. In a client that renders [MCP Apps](https://github.com/modelcontextprotocol/ext-apps)
  140. (Claude Desktop and claude.ai), a film or series comes back as a card rather
  141. than a line of text. `get_media_details` shows one card: poster, blurred
  142. backdrop, synopsis, genres, runtime or seasons, episode progress, a status badge
  143. (available, monitored, downloading, unmonitored, not in library) with the
  144. quality profile, and links to TMDB and IMDb. `search_media` and
  145. `get_library` show a grid of up to twenty posters, each with its status.
  146. <img src="screenshots/cards-detail-dark.png" alt="A detail card: poster, title and year, Series and Monitored badges, quality profile, seasons and genres, an episode progress bar, the synopsis and TMDB and IMDb links" width="560">
  147. <img src="screenshots/cards-grid-light.png" alt="A grid of poster tiles, each with its status as a labelled pill on the poster, then its title, year and type; one tile without artwork shows its title on a plain background" width="560">
  148. **Nothing to configure, and no TMDB key.** The artwork is what Radarr and Sonarr
  149. already hold (`remoteUrl`, from TMDB and TheTVDB) and the poster paths Seerr
  150. returns from TMDB. The card loads those images straight from `image.tmdb.org`
  151. and `artworks.thetvdb.com`, the only hosts its CSP allows; your services' own
  152. addresses and API keys never reach it. A title with no artwork, or whose image
  153. will not load, gets a plain tile with its name.
  154. **Nothing changes for any other client.** The text answer and
  155. `structuredContent` are identical. The cards ride in the result's `_meta`, which
  156. is not model context, and are only built for a client that says it renders MCP
  157. Apps, or one that says nothing (stateless HTTP). `tools.media_cards: false` turns
  158. them off. The cards are read-only for now.
  159. ## What it costs your context
  160. One server in front of nineteen services is the whole idea, and it would be a
  161. poor trade if it arrived as a wall of text. Every tool's name, description and
  162. schemas sit in your client's context from the moment it connects, so that bill
  163. is measured and capped rather than left to grow:
  164. - **Forty-four tools, and a forty-fifth fails the build.** Accuracy drops
  165. measurably past roughly forty of them, so new capability extends a tool
  166. wherever it fits.
  167. - **A description stays under 1,000 characters**, and 29,000 for all of them
  168. together. It says what the tool is for and what makes a call go wrong; the
  169. field-by-field reference is a resource, read only when a client asks for it.
  170. - **Your stack decides what is sent.** A write tool for a service you do not
  171. run is never listed, nor a kind nothing in your library holds, nor a sentence
  172. about Lidarr on a stack with no Lidarr. Radarr, Sonarr, SABnzbd and Jellyfin
  173. come to 36 tools and roughly 20,700 tokens, against 28,000 with everything
  174. listed.
  175. - **The answers are shaped the same way.** The default `detail` is the cheap
  176. one, every list is paged and says when it was cut, and the poster cards ride
  177. in `_meta` rather than in the model's context.
  178. [What a session costs](docs/tools.md#what-a-session-costs) has the figures per
  179. stack and everything that is trimmed.
  180. ## Documentation
  181. | | |
  182. | --- | --- |
  183. | **[Tools](docs/tools.md)** | All forty-four, what each answers, and the fields whose meaning is not obvious |
  184. | **[Writes](docs/writes.md)** | Turning them on, the two tiers, and the preview-and-confirm handshake |
  185. | **[Configuration](docs/configuration.md)** | `config.yaml`, the nine services that take a list, Jellyfin's `default_user`, running Plex and Jellyfin side by side |
  186. | **[Config UI](docs/config-ui.md)** | The six pages, and what each does that is not obvious |
  187. | **[Management API](docs/api.md)** | JSON API for companion apps to see and manage services, settings and tokens, with named read or admin keys you create on the config page |
  188. | **[IMDb ratings](docs/imdb.md)** | The only way to get an IMDb score for a series, and what it costs |
  189. | **[Security](docs/security.md)** | The threat model, walked against the OWASP MCP Top 10, including what it does not solve |
  190. | **[Contributing](CONTRIBUTING.md)** | [Which services qualify](CONTRIBUTING.md#which-services-qualify), how to add an adapter, and the rules an AI agent tends to break |
  191. ## Requirements
  192. - At least one supported service, LAN-reachable: Radarr 4.0+, Sonarr 4.0+,
  193. Whisparr 2.x (V2 only, not Eros), Prowlarr 1.0+, Bazarr 1.4+, Jellyfin 10.9+, Plex Media Server (no minimum enforced; verified on 1.43),
  194. Seerr 1.0+, SABnzbd 3.0+, NZBGet 21.0+, Transmission 3.0+, qBittorrent 4.1+, Profilarr 2.2.0+, Cleanuparr 2.10.0+, Reclaimerr 0.6.0+, Dispatcharr 0.33.0+, Shelfmark 1.5.0+, Grimmory 3.5.0+
  195. - Lidarr 2.1.3+ for reading, monitoring, adding, changing and deleting artists,
  196. its queue, its wanted list and calendar, release search, `diagnose_media`,
  197. `trigger_scan`, `fix_metadata` and `get_stack_health`. Artists join to
  198. Jellyfin and Plex on the MusicBrainz artist id; [Tools](docs/tools.md) says
  199. what each tool does with them.
  200. - Docker, or Node 24+ to run from source
  201. - An MCP client. Protocol revision `2026-07-28` is the native one; clients on a
  202. 2025-era revision are still served
  203. The tool surface is the public API: renaming or removing a tool, a parameter or
  204. a response field is a **major**, because that break is silent: a model stops
  205. finding a renamed tool rather than raising an error. 2.0.0 removed what 1.x
  206. had deprecated; the [changelog](CHANGELOG.md) lists each name with its
  207. replacement.
  208. ## Contributing
  209. **Contributions are welcome, and new service adapters most of all**: Emby and
  210. Deluge would both be accepted today, and
  211. [the list says so in advance](CONTRIBUTING.md#what-would-be-accepted-today),
  212. along with the ones that would not be. An adapter is deliberately the most
  213. self-contained thing in the codebase. Two things to know first: not every
  214. service qualifies ([which services qualify](CONTRIBUTING.md#which-services-qualify)),
  215. and **I cannot test a service I do not run**, so the second bar is that you tested
  216. it against your own live instance and the PR says what you tested and against
  217. which version.
  218. **One adapter remains unverified: qBittorrent.** The maintainer runs neither
  219. Plex, qBittorrent nor NZBGet, so testing means running a build against your own
  220. server and reporting what worked. Plex and NZBGet have been verified live by
  221. volunteers and contributors; [qBittorrent](../../issues/147) still waits on
  222. that kind of report. [The design behind Plex, and what else is on the
  223. list](CONTRIBUTING.md#what-would-be-accepted-today).
  224. **AI-assisted contributions are welcome**, held to the same bar and no other;
  225. arr-mcp is itself built with a coding agent. Point yours at
  226. [CONTRIBUTING.md](CONTRIBUTING.md#if-you-are-working-with-a-coding-agent).
  227. **Missing a tool?** [Open an issue](../../issues/new/choose) describing the
  228. question you could not get answered rather than the tool you think should
  229. exist. Often the answer is a new parameter on one that already exists.
  230. ## Security
  231. arr-mcp is **not designed to be exposed to the internet.** The `/mcp` endpoint
  232. requires a bearer token because "LAN-only" is a network assumption rather than a
  233. security control. It fronts every service credential you configure and, once enabled, file
  234. deletion, and a home network contains guest phones and IoT devices. Put it
  235. behind a reverse proxy with TLS if it needs to leave the LAN, and pin
  236. `allowed_hosts` if you do.
  237. Beyond the network: writes are off until you enable them, every write is
  238. previewed and confirmed before it acts, and everything a service returns is
  239. fenced as data rather than instruction. Service credentials need not sit in
  240. `config.yaml` either: `api_key_file` and `password_file` read a Docker, Podman
  241. or systemd secret, and `${NAME}` reads an environment variable
  242. ([secrets from files or the environment](docs/configuration.md#secrets-from-files-or-the-environment)).
  243. [Security](docs/security.md) walks all of it against the OWASP MCP Top 10, and
  244. is equally explicit about what it does not solve. Found something?
  245. [SECURITY.md](SECURITY.md).
  246. ## Contributors
  247. Everyone who has had a pull request merged into arr-mcp. The grid updates on its
  248. own as new contributors land, though it can take a few days to catch up.
  249. [![Contributors](https://contrib.rocks/image?repo=Bardesss/arr-mcp)](https://github.com/Bardesss/arr-mcp/graphs/contributors)
  250. The grid only shows commits tied to a GitHub account, so it misses
  251. [@itapai](https://github.com/itapai) ([#249](../../pull/249)).
  252. Testing counts as much as code here. Plex is verified because of [@Svnow132](https://github.com/Svnow132)
  253. ([#180](../../issues/180)) and [@davidgibbons](https://github.com/davidgibbons)
  254. ([#312](../../issues/312)).
  255. ## Thanks
  256. arr-mcp is glue; the hard parts belong to other people. Nearly every service it
  257. speaks to is free software maintained largely by volunteers: [Radarr](https://radarr.video),
  258. [Sonarr](https://sonarr.tv), [Whisparr](https://github.com/Whisparr/Whisparr), [Lidarr](https://lidarr.audio),
  259. [Prowlarr](https://prowlarr.com),
  260. [Bazarr](https://www.bazarr.media), [Jellyfin](https://jellyfin.org),
  261. [Seerr](https://github.com/seerr-team/seerr), [SABnzbd](https://sabnzbd.org),
  262. [NZBGet](https://nzbget.com), [Transmission](https://transmissionbt.com), [qBittorrent](https://www.qbittorrent.org),
  263. [Profilarr](https://github.com/Dictionarry-Hub/profilarr), [Cleanuparr](https://github.com/Cleanuparr/Cleanuparr), [Reclaimerr](https://github.com/jessielw/Reclaimerr), [Dispatcharr](https://github.com/Dispatcharr/Dispatcharr), [Shelfmark](https://github.com/calibrain/shelfmark), [Grimmory](https://github.com/grimmory-tools/grimmory), as are the libraries it is built
  264. on: [MCP TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk),
  265. [Hono](https://hono.dev), [Zod](https://zod.dev), [Pino](https://getpino.io),
  266. [Vitest](https://vitest.dev), [yaml](https://eemeli.org/yaml/) and
  267. [TypeScript](https://www.typescriptlang.org). If you find arr-mcp useful,
  268. consider supporting them first. [Plex](https://www.plex.tv) is the exception: a
  269. commercial product, but its API carries as much of the work as the rest.
  270. When you enable the [IMDb dataset](docs/imdb.md): information courtesy of
  271. [IMDb](https://www.imdb.com), used with permission, for personal and
  272. non-commercial use.
  273. ## Licence
  274. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.