mcp-arr
MCP server for *arr media management suite
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
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/aplaceforallmystuff/mcp-arr 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/aplaceforallmystuff/mcp-arr'
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
Markdown
[](/listings/aplaceforallmystuff--mcp-arr)HTML
<a href="/listings/aplaceforallmystuff--mcp-arr"><img src="/api/listings/aplaceforallmystuff--mcp-arr/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Using npm (Recommended)
npx mcp-arr-server
Remote HTTP Mode
MCP_TRANSPORT=http PORT=3000 npx mcp-arr-server
By default the remote server listens on `127.0.0.1:3000` and serves MCP on `/mcp`.
Environment variables for remote mode:
- `MCP_TRANSPORT=http` to enable remote Streamable HTTP transport - `HOST` to override the bind host (default `127.0.0.1`) - `PORT` to override the port (default `3000`) - `MCP_PATH` to override the MCP endpoint path (default `/mcp`)
Docker
Prebuilt images are published to GitHub Container Registry on every release. You do not need to build anything:
docker pull ghcr.io/aplaceforallmystuff/mcp-arr:latest
Tags follow the release version — `latest`, `1`, `1.7`, and each exact version such as `1.7.3`. Pin to a major or minor tag if you want updates without surprises.
Run in local stdio mode:
docker run --rm -i \ -e SONARR_URL=http://host.docker.internal:8989 \ -e SONARR_API_KEY=your-sonarr-api-key \ ghcr.io/aplaceforallmystuff/mcp-arr:latest
Run in remote HTTP mode:
docker run --rm -p 3000:3000 \ -e MCP_TRANSPORT=http \ -e HOST=0.0.0.0 \ -e PORT=3000 \ -e SONARR_URL=http://host.docker.internal:8989 \ -e SONARR_API_KEY=your-sonarr-api-key \ ghcr.io/aplaceforallmystuff/mcp-arr:latest
Minimal `docker-compose.yml`:
services:
mcp-arr:
image: ghcr.io/aplaceforallmystuff/mcp-arr:latest
ports:
- "3000:3000"
environment:
MCP_TRANSPORT: http
HOST: 0.0.0.0
PORT: 3000
SONARR_URL: http://host.docker.internal:8989
SONARR_API_KEY: your-sonarr-api-key
RADARR_URL: http://host.docker.internal:7878
RADARR_API_KEY: your-radarr-api-keyBuilding it yourself
Only needed if you are developing against a change that is not released yet:
docker build -t mcp-arr .
From Source
git clone https://github.com/aplaceforallmystuff/mcp-arr.git cd mcp-arr npm install npm run build
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 · 464 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.
- # MCP *arr Server
- 
- <!-- <p align="center">
- <img src="docs/mcp-arr-logo.png" alt="MCP *arr Server" width="400">
- </p> -->
- [](https://oathe.ai/report/aplaceforallmystuff/mcp-arr)
- [](https://www.npmjs.com/package/mcp-arr-server)
- [](https://github.com/aplaceforallmystuff/mcp-arr/actions/workflows/ci.yml)
- [](https://opensource.org/licenses/MIT)
- [](https://modelcontextprotocol.io)
- MCP server for the [*arr media management suite](https://wiki.servarr.com/) - Sonarr, Radarr, Lidarr, and Prowlarr.
- Supports both local `stdio` mode for Claude/Codex-style clients and remote HTTP mode for hosted MCP clients such as ChatGPT connectors.
- ## Why Use This?
- - **Unified media management** - Control all your *arr applications from one interface
- - **Natural language queries** - Ask about your library in plain English
- - **Cross-service search** - Find content across TV, movies, and music simultaneously
- - **Download monitoring** - Check queue status and progress across all services
- - **Calendar integration** - See upcoming releases for all media types
- - **Configuration review** - Get AI-powered suggestions for optimizing your setup
- - **Flexible configuration** - Enable only the services you use
- ## Features
- | Category | Capabilities |
- |----------|-------------|
- | **Sonarr (TV)** | List series, view episodes, search shows, trigger downloads, check queue, view calendar, review setup |
- | **Radarr (Movies)** | List movies, search films, trigger downloads, check queue, view releases, review setup |
- | **Lidarr (Music)** | List artists, view albums, search musicians, trigger downloads, check queue, view calendar, review setup |
- | **Prowlarr (Indexers)** | List indexers, search across all trackers, test health, view statistics |
- | **Cross-Service** | Status check, unified search across all configured services |
- | **Configuration** | Quality profiles, download clients, naming conventions, health checks, storage info |
- | **TRaSH Guides** | Reference quality profiles, custom formats, naming conventions, compare against recommendations |
- ## Prerequisites
- - Node.js 20+ for HTTP mode. Node.js 18 builds, but valid HTTP requests return HTTP 400 in the verified baseline and v1.7.4 candidate. Use Node.js 20 or newer for HTTP clients.
- - At least one *arr application running with API access:
- - [Sonarr](https://sonarr.tv/) for TV series
- - [Radarr](https://radarr.video/) for movies
- - [Lidarr](https://lidarr.audio/) for music
- - [Prowlarr](https://prowlarr.com/) for indexer management
- ## Installation
- ### Using npm (Recommended)
- ```bash
- npx mcp-arr-server
- ```
- ### Remote HTTP Mode
- ```bash
- MCP_TRANSPORT=http PORT=3000 npx mcp-arr-server
- ```
- By default the remote server listens on `127.0.0.1:3000` and serves MCP on `/mcp`.
- Environment variables for remote mode:
- - `MCP_TRANSPORT=http` to enable remote Streamable HTTP transport
- - `HOST` to override the bind host (default `127.0.0.1`)
- - `PORT` to override the port (default `3000`)
- - `MCP_PATH` to override the MCP endpoint path (default `/mcp`)
- ### Docker
- Prebuilt images are published to GitHub Container Registry on every release. You do not need to
- build anything:
- ```bash
- docker pull ghcr.io/aplaceforallmystuff/mcp-arr:latest
- ```
- Tags follow the release version — `latest`, `1`, `1.7`, and each exact version such as `1.7.3`.
- Pin to a major or minor tag if you want updates without surprises.
- Run in local stdio mode:
- ```bash
- docker run --rm -i \
- -e SONARR_URL=http://host.docker.internal:8989 \
- -e SONARR_API_KEY=your-sonarr-api-key \
- ghcr.io/aplaceforallmystuff/mcp-arr:latest
- ```
- Run in remote HTTP mode:
- ```bash
- docker run --rm -p 3000:3000 \
- -e MCP_TRANSPORT=http \
- -e HOST=0.0.0.0 \
- -e PORT=3000 \
- -e SONARR_URL=http://host.docker.internal:8989 \
- -e SONARR_API_KEY=your-sonarr-api-key \
- ghcr.io/aplaceforallmystuff/mcp-arr:latest
- ```
- Minimal `docker-compose.yml`:
- ```yaml
- services:
- mcp-arr:
- image: ghcr.io/aplaceforallmystuff/mcp-arr:latest
- ports:
- - "3000:3000"
- environment:
- MCP_TRANSPORT: http
- HOST: 0.0.0.0
- PORT: 3000
- SONARR_URL: http://host.docker.internal:8989
- SONARR_API_KEY: your-sonarr-api-key
- RADARR_URL: http://host.docker.internal:7878
- RADARR_API_KEY: your-radarr-api-key
- ```
- #### Building it yourself
- Only needed if you are developing against a change that is not released yet:
- ```bash
- docker build -t mcp-arr .
- ```
- ### From Source
- ```bash
- git clone https://github.com/aplaceforallmystuff/mcp-arr.git
- cd mcp-arr
- npm install
- npm run build
- ```
- ## Configuration
- ### Getting API Keys
- Each *arr application has an API key in Settings > General > Security:
- 1. Open your *arr application's web interface
- 2. Go to **Settings** > **General**
- 3. Find the **API Key** under the Security section
- 4. Copy the API key for use in configuration
- ### For Claude Desktop
- Add to your Claude Desktop config file:
- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
- ```json
- {
- "mcpServers": {
- "arr": {
- "command": "npx",
- "args": ["-y", "mcp-arr-server"],
- "env": {
- "SONARR_URL": "http://localhost:8989",
- "SONARR_API_KEY": "your-sonarr-api-key",
- "RADARR_URL": "http://localhost:7878",
- "RADARR_API_KEY": "your-radarr-api-key",
- "LIDARR_URL": "http://localhost:8686",
- "LIDARR_API_KEY": "your-lidarr-api-key",
- "PROWLARR_URL": "http://localhost:9696",
- "PROWLARR_API_KEY": "your-prowlarr-api-key"
- }
- }
- }
- }
- ```
- ### For Claude Code
- Add to `~/.claude.json`:
- ```json
- {
- "mcpServers": {
- "arr": {
- "command": "npx",
- "args": ["-y", "mcp-arr-server"],
- "env": {
- "SONARR_URL": "http://localhost:8989",
- "SONARR_API_KEY": "your-sonarr-api-key",
- "RADARR_URL": "http://localhost:7878",
- "RADARR_API_KEY": "your-radarr-api-key"
- }
- }
- }
- }
- ```
- **Note**: Only configure the services you have running. The server automatically detects which services are available based on the environment variables you provide.
- **TRaSH-only mode**: if you don’t configure any *arr services, the server still starts and exposes the TRaSH Guides reference tools plus generic `search` and `fetch`.
- **Read-only mode**: set `ARR_READ_ONLY=true` to hide every tool that changes state (searches, refreshes, adds, updates, deletes, release grabs and manual imports) from `tools/list` and refuse calls to them. A tool counts as read-only when its `readOnlyHint` annotation is `true`.
- ## ChatGPT / Remote MCP
- To use `mcp-arr` with ChatGPT, run the server in remote HTTP mode on a reachable host and connect ChatGPT to the `/mcp` endpoint.
- The server now exposes the generic `search` and `fetch` tools expected by ChatGPT-style remote MCP integrations:
- - `search` discovers matching *arr media and TRaSH profiles
- - `fetch` returns structured detail for a selected search result
- The existing service-specific tools remain available for richer local or power-user workflows.
- ## Usage Examples
- ### Library Management
- - "Show me all my TV series"
- - "What movies do I have in Radarr?"
- - "List all artists in my music library"
- ### Searching & Adding Content
- - "Search for sci-fi shows on Sonarr"
- - "Find action movies from the 90s"
- - "Add this show to my TV library"
- - "Add that movie to Radarr"
- - "Search for jazz albums and add this artist"
- - "Add this movie with my '4k' tag"
- - "What tags do I have in Sonarr?"
- ### Download Queue
- - "What's downloading right now?"
- - "Check the Sonarr queue"
- - "Show Radarr download progress"
- ### Upcoming Releases
- - "What TV episodes are coming this week?"
- - "Show upcoming movie releases"
- - "Any new albums coming out this month?"
- ### Downloading Content
- - "What episodes of this show am I missing?"
- - "Download the missing episodes for that series"
- - "Search for this specific movie"
- - "Grab that album I'm missing"
- ### Indexer Management
- - "Are my indexers healthy?"
- - "How are my indexers performing?"
- - "Test all my Prowlarr indexers"
- ### Configuration Review
- - "Review my Sonarr setup and suggest improvements"
- - "Show me my quality profiles in Radarr"
- - "Are there any health issues with my Lidarr?"
- - "What naming convention am I using for TV shows?"
- - "Help me understand my quality profiles - why am I not getting 4K?"
- - "Check my download client configuration"
- - "How much free space do I have on my root folders?"
- ### Cross-Service
- - "Check status of all my *arr services"
- - "Search for 'comedy' across all services"
- ## Available Tools
- ### Radarr manual import
- Use `radarr_get_manual_import_candidates` to inspect a completed download folder or download ID. Review exact paths, movie mappings, sizes, quality, languages and rejection reasons before calling `radarr_manual_import`. Import requires `confirmed=true`, 1–25 selected files with expected sizes, and an explicit `auto`, `copy` or `move` mode. A fresh scan must still match each selection. Duplicate paths or movie selections, unknown metadata, changed download IDs and substantive rejections are refused. Preference overrides use the same narrow recognized reasons as exact release grabs and require exact current acknowledgements.
- Radarr may replace existing library files. `copy` preserves the download source; `move` can remove it; `auto` follows Radarr download-client rules. A response with `submitted=true` and `imported=false` means only that Radarr accepted a command. Use `radarr_get_command` and inspect the resulting movie files and queue before treating the import as complete or retrying.
- ### Exact release grabs
- Use `sonarr_grab_release` or `radarr_grab_release` only after the user approves the exact media ID, indexer ID and GUID. Both require `confirmed=true` and re-query current releases before submitting one download. Missing, ambiguous or download-disallowed candidates are refused.
- Rejection overrides require exact current `acknowledgedRejections` strings. Supported preference reasons are `Not an upgrade`, `Existing file meets cutoff`, and cutoff reasons naming a Remux/Bluray/WEBDL/WEBRip/HDTV quality at 720p, 1080p or 2160p. Unknown wording and substantive rejections are refused. After an ambiguous submission, inspect the queue and library before retrying.
- ### Release inspection
- Use `sonarr_get_episode_releases` or `radarr_get_movie_releases` to inspect interactive indexer results without starting downloads. Responses include exact GUID/indexer IDs, sizes, languages, quality, availability and rejection reasons. Pagination limits the response, not the underlying indexer search.
- ### Queue diagnostics
- Paginated queue responses include `statusMessages`, `downloadId`, `outputPath`, `sizeBytes` and `sizeLeftBytes`. These fields help distinguish failed downloads from completed downloads awaiting import. Queue absence alone does not establish success or failure. Output paths refer to the configured server filesystem.
- ### Add Sonarr and Radarr file metadata tools
- Inspect existing episode and movie files with paginated summary or full MediaInfo responses. Defaults to 25 records; limit is capped at 100. No media files are opened or changed.
- - `sonarr_get_episode_files`
- - `radarr_get_movie_files`
- ### General Tools
- | Tool | Description |
- |------|-------------|
- | `arr_status` | Get connection status for all configured *arr services |
- | `arr_search_all` | Search across all configured services simultaneously |
- | `search` | Generic discovery tool for remote MCP clients such as ChatGPT |
- | `fetch` | Generic detail-fetch tool for items returned by `search` |
- ### Sonarr Tools (TV)
- | Tool | Description |
- |------|-------------|
- | `sonarr_get_series` | List TV series in your library, optionally sorted by date added or size on disk |
- | `sonarr_search` | Search for TV series by name (returns tvdbId for adding) |
- | `sonarr_add_series` | Add a TV series to Sonarr (supports tags) |
- | `sonarr_get_root_folders` | Get available root folders for adding series |
- | `sonarr_get_quality_profiles` | Get available quality profiles for adding series |
- | `sonarr_get_queue` | View current download queue with `limit` and `offset` pagination |
- | `sonarr_get_calendar` | See upcoming episodes |
- | `sonarr_get_episodes` | List episodes for a series (shows missing vs available) |
- | `sonarr_search_missing` | Trigger search for all missing episodes in a series |
- | `sonarr_search_episode` | Trigger search for specific episode(s) |
- | `sonarr_refresh_series` | Trigger a metadata refresh for a specific series in Sonarr |
- ### Radarr Tools (Movies)
- | Tool | Description |
- |------|-------------|
- | `radarr_get_movies` | List movies in your library, optionally sorted by date added or size on disk |
- | `radarr_search` | Search for movies by name (returns tmdbId for adding) |
- | `radarr_add_movie` | Add a movie to Radarr (supports tags) |
- | `radarr_get_root_folders` | Get available root folders for adding movies |
- | `radarr_get_quality_profiles` | Get available quality profiles for adding movies |
- | `radarr_get_queue` | View current download queue with `limit` and `offset` pagination |
- | `radarr_get_calendar` | See upcoming releases |
- | `radarr_search_movie` | Trigger search to download a movie in your library |
- | `radarr_search_movies` | Bulk-trigger searches for multiple movie IDs at once |
- | `radarr_update_movie` | Update a movie's quality profile, monitored status, minimum availability, tags, or path |
- | `radarr_delete_queue_item` | Remove an item from the download queue (optionally blocklist the release) |
- | `radarr_refresh_movie` | Trigger a metadata refresh for a specific movie in Radarr |
- ### Lidarr Tools (Music)
- | Tool | Description |
- |------|-------------|
- | `lidarr_get_artists` | List all artists in your library |
- | `lidarr_search` | Search for artists by name (returns foreignArtistId for adding) |
- | `lidarr_add_artist` | Add an artist to Lidarr (supports tags) |
- | `lidarr_get_root_folders` | Get available root folders for adding artists |
- | `lidarr_get_quality_profiles` | Get available quality profiles for adding artists |
- | `lidarr_get_metadata_profiles` | Get available metadata profiles for adding artists |
- | `lidarr_get_queue` | View current download queue with `limit` and `offset` pagination |
- | `lidarr_get_albums` | List albums for an artist (shows missing vs available) |
- | `lidarr_search_album` | Trigger search for a specific album |
- | `lidarr_search_missing` | Trigger search for all missing albums for an artist |
- | `lidarr_get_calendar` | See upcoming album releases |
- ### Prowlarr Tools (Indexers)
- | Tool | Description |
- |------|-------------|
- | `prowlarr_get_indexers` | List all configured indexers |
- | `prowlarr_search` | Search across all indexers |
- | `prowlarr_test_indexers` | Test all indexers and return health status |
- | `prowlarr_get_stats` | Get indexer statistics (queries, grabs, failures) |
- ### Configuration Review Tools
- These tools are available for Sonarr, Radarr, and Lidarr. Replace `{service}` with the service name (e.g., `sonarr_get_quality_profiles`).
- | Tool | Description |
- |------|-------------|
- | `{service}_get_quality_profiles` | Detailed quality profile information with allowed qualities and custom format scores |
- | `{service}_get_health` | Health check warnings and issues detected by the application |
- | `{service}_get_root_folders` | Storage paths, free space, and accessibility status |
- | `{service}_get_download_clients` | Download client configurations and settings |
- | `{service}_get_naming` | File and folder naming conventions |
- | `{service}_get_tags` | Tag definitions for content organization |
- | `{service}_review_setup` | **Comprehensive configuration dump for AI-assisted setup analysis** |
- The `{service}_review_setup` tool returns all configuration in a single call, enabling natural language conversations about optimizing your setup. Claude can analyze your quality profiles, suggest improvements, explain why certain content isn't being grabbed, and help configure complex settings like custom formats.
- > **⚠️ Disclaimer**: The configuration review tools provide **read-only** access to your *arr settings. Any changes to your configuration must be made directly in the *arr application interfaces. The AI's suggestions are recommendations only - always back up your configuration before making significant changes. The maintainers are not responsible for any configuration changes, data loss, or other issues that may arise from following AI-generated recommendations.
- ### TRaSH Guides Tools
- Access community-curated quality profiles, custom formats, and naming conventions from [TRaSH Guides](https://trash-guides.info/) directly through Claude or ChatGPT. These tools work without any *arr configuration - they fetch reference data from the TRaSH Guides GitHub repository.
- | Tool | Description |
- |------|-------------|
- | `trash_list_profiles` | List available TRaSH quality profiles for Radarr or Sonarr |
- | `trash_get_profile` | Get detailed profile with custom formats, scores, and quality settings |
- | `trash_list_custom_formats` | List custom formats with optional category filter (hdr, audio, resolution, etc.) |
- | `trash_get_naming` | Get recommended naming conventions for Plex, Emby, Jellyfin, or standard |
- | `trash_get_quality_sizes` | Get recommended min/max/preferred sizes for each quality level |
- | `trash_compare_profile` | Compare your profile against TRaSH recommendations (requires *arr configured) |
- | `trash_compare_naming` | Compare your naming config against TRaSH recommendations (requires *arr configured) |
- **Example usage:**
- - "What quality profiles does TRaSH recommend for 4K movies?"
- - "Show me the remux-web-1080p profile details"
- - "Compare my Radarr profile 4 against the TRaSH uhd-bluray-web profile"
- - "What naming convention should I use for Plex?"
- - "List HDR-related custom formats for Radarr"
- Data is cached for 1 hour to minimize GitHub API calls.
- ## Development
- ```bash
- # Watch mode for development
- npm run watch
- # Build TypeScript
- npm run build
- # Run locally
- SONARR_URL="http://localhost:8989" SONARR_API_KEY="your-key" node dist/index.js
- ```
- ## Troubleshooting
- ### "No *arr services configured"
- Ensure you have set at least one pair of URL and API_KEY environment variables:
- ```bash
- SONARR_URL="http://localhost:8989"
- SONARR_API_KEY="your-api-key"
- ```
- ### "API error: 401 Unauthorized"
- The API key is incorrect. Verify it in your *arr application under Settings > General > Security.
- ### "fetch failed" or "ECONNREFUSED"
- The *arr application is not running or the URL is incorrect. Verify:
- - The application is running
- - The URL and port are correct
- - There's no firewall blocking the connection
- ### "Sonarr/Radarr/etc not configured"
- You tried to use a tool for a service that isn't configured. Add the corresponding URL and API_KEY environment variables.
- ### "SONARR_URL must be a full http:// or https:// URL"
- The server stops at startup when a configured service URL has no `http://` or `https://` scheme, for example `localhost:8989`. Use the full URL, such as `http://localhost:8989`.
- ### "Invalid arguments for ..."
- Tool arguments are checked against the tool's input schema before any request is sent. IDs must be positive integers, and booleans, enums and limits must match the schema.
- ## Need help building or securing MCP servers?
- I build and maintain MCP servers like this one, and I review AI and agent setups for security. If your team needs a custom server, an integration, or a security review of one you already run, see [jimchristian.net/work](https://jimchristian.net/work/) or book a [discovery session](https://jimchristian.net/discovery/).
- ## Contributing
- See [CONTRIBUTING.md](CONTRIBUTING.md) for setup, checks, and tool changes.
- ## License
- MIT - see [LICENSE](LICENSE) for details.
- ## Links
- - [Servarr Wiki](https://wiki.servarr.com/) - Documentation for all *arr applications
- - [TRaSH Guides](https://trash-guides.info/) - Quality profiles, custom formats, and setup guides
- - [Sonarr API Docs](https://sonarr.tv/docs/api/)
- - [Model Context Protocol](https://modelcontextprotocol.io)
- - [GitHub Repository](https://github.com/aplaceforallmystuff/mcp-arr)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.