Arr Media ManagerSAFE
MCP server for *arr media management suite
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](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 - 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 f
eb0b7f1ffd2cOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-arr-server --env SONARR_API_KEY=${SONARR_API_KEY} --env RADARR_API_KEY=${RADARR_API_KEY} --env LIDARR_API_KEY=${LIDARR_API_KEY} --env PROWLARR_API_KEY=${PROWLARR_API_KEY} -- npx -y [email protected]Exposed tools (44)
31 read · 12 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
arr_search_all | read | Search across all configured *arr services for any media |
fetch | read | Fetch a specific item returned by search. Accepts an opaque item id from the search tool. |
lidarr_add_artist | write | Add an artist to Lidarr. Use lidarr_search first to find the foreignArtistId, and lidarr_get_root_folders / lidarr_get_quality_profiles / lidarr_get_metadata_profiles to get valid values. Use lidarr_get_tags to get valid tag IDs. |
lidarr_get_albums | read | Get albums for an artist in Lidarr. Shows which albums are available and which are missing. |
lidarr_get_artists | read | Get all artists in Lidarr library |
lidarr_get_calendar | read | Get upcoming album releases from Lidarr |
lidarr_get_metadata_profiles | read | Get available metadata profiles for Lidarr. Use this to find valid metadataProfileId values when adding an artist. |
lidarr_get_quality_profiles | read | Get available quality profiles for Lidarr. Use this to find valid qualityProfileId values when adding an artist. |
lidarr_get_queue | read | Get Lidarr download queue. Supports pagination with limit and offset. |
lidarr_get_root_folders | read | Get available root folders for Lidarr. Use this to find valid rootFolderPath values when adding an artist. |
lidarr_search | read | Search for artists by name. Returns results with foreignArtistId needed for lidarr_add_artist. |
lidarr_search_album | write | Trigger a search for a specific album to download |
lidarr_search_missing | write | Trigger a search for all missing albums for an artist |
prowlarr_get_indexers | read | Get all configured indexers in Prowlarr |
prowlarr_get_stats | read | Get indexer statistics (queries, grabs, failures) |
prowlarr_search | read | Search across all Prowlarr indexers |
prowlarr_test_indexers | read | Test all indexers and return their health status |
radarr_add_movie | write | Add a movie to Radarr. Use radarr_search first to find the tmdbId, and radarr_get_root_folders / radarr_get_quality_profiles to get valid values. Use radarr_get_tags to get valid tag IDs. |
radarr_delete_queue_item | destructive | Remove an item from the Radarr download queue. Use radarr_get_queue to find queue item IDs. Can optionally blocklist the release to prevent re-grabbing. |
radarr_get_calendar | read | Get upcoming movie releases from Radarr |
radarr_get_movies | read | Get movies from Radarr library with optional pagination and title filtering. Defaults to limit=25 to avoid very large responses. Use offset to fetch additional pages. |
radarr_get_queue | read | Get Radarr download queue. Supports pagination with limit and offset. |
radarr_refresh_movie | write | Trigger a metadata refresh for a specific movie in Radarr |
radarr_search | read | Search for movies by name. Returns results with tmdbId needed for radarr_add_movie. |
radarr_search_movie | write | Trigger a search to download a movie that |
radarr_search_movies | write | Trigger a search for multiple movies at once. Accepts an array of movie IDs. Use this for bulk upgrade requests instead of calling radarr_search_movie one at a time. |
radarr_update_movie | write | Update a movie in Radarr. Can change qualityProfileId, monitored status, minimumAvailability, tags, and path. Fetches the full movie object, applies your changes, and PUTs it back. |
search | read | Search across configured *arr libraries plus TRaSH Guides reference profiles. This is the primary discovery tool for remote MCP clients such as ChatGPT. |
sonarr_add_series | write | Add a TV series to Sonarr. Use sonarr_search first to find the tvdbId, and sonarr_get_root_folders / sonarr_get_quality_profiles to get valid values for rootFolderPath and qualityProfileId. Use sonarr_get_tags to get valid tag IDs. |
sonarr_get_calendar | read | Get upcoming TV episodes from Sonarr |
sonarr_get_episodes | read | Get episodes for a TV series. Shows which episodes are available and which are missing. |
sonarr_get_queue | read | Get Sonarr download queue. Supports pagination with limit and offset. |
sonarr_get_series | read | Get TV series from Sonarr library with optional pagination and title filtering. Defaults to limit=25 to avoid very large responses. Use offset to fetch additional pages. |
sonarr_refresh_series | write | Trigger a metadata refresh for a specific series in Sonarr |
sonarr_search | read | Search for TV series by name. Returns results with tvdbId needed for sonarr_add_series. |
sonarr_search_episode | write | Trigger a search for specific episode(s) |
sonarr_search_missing | write | Trigger a search for all missing episodes in a series |
trash_compare_naming | read | Compare your naming configuration against TRaSH Guides recommendations. Requires the corresponding *arr service to be configured. |
trash_compare_profile | read | Compare your quality profile against TRaSH Guides recommendations. Shows missing custom formats, scoring differences, and quality settings. Requires the corresponding *arr service to be configured. |
trash_get_naming | read | Get TRaSH Guides recommended naming conventions for your media server (Plex, Emby, Jellyfin, or standard) |
trash_get_profile | read | Get a specific TRaSH Guides quality profile with all custom format scores, quality settings, and implementation details |
trash_get_quality_sizes | read | Get TRaSH Guides recommended min/max/preferred sizes for each quality level |
trash_list_custom_formats | read | List available TRaSH Guides custom formats. Can filter by category: hdr, audio, resolution, source, streaming, anime, unwanted, release, language |
trash_list_profiles | read | List available TRaSH Guides quality profiles for Radarr or Sonarr. Shows recommended profiles for different use cases (1080p, 4K, Remux, etc.) |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (11)
radarr_delete_queue_item
CLAUDE.md
GEMINI.md
const response = await fetch(`http://127.0.0.1:${port}/health`);return fetch(`http://127.0.0.1:${port}/mcp`, {[) to clear five advisories affecting `hono <= 4.12.24`: CORS middleware reflecting any origin
docs/mcp-arr-icon.png
docs/mcp-arr-logo.png
check: All service access via environment variables
Gates applied: no_behavioural_pass.
eb0b7f1ffd2cfull audit observations/trust-audit/mcp-server/aplaceforallmystuff__arr-media-manager.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | eb0b7f1ffd2c | SAFE | B | 89 | first audit |
Questions
What is the Arr Media Manager MCP server?
MCP server for *arr media management suite
What tools does Arr Media Manager expose?
44 in total: 31 read-only, 12 that write, and 1 that can delete or overwrite (radarr_delete_queue_item). Every one is listed on this page with its risk.
Is Arr Media Manager safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Arr Media Manager need?
It reads LIDARR_API_KEY, PROWLARR_API_KEY, RADARR_API_KEY and SONARR_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Arr Media Manager run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-arr-server at 1.7.3.
How current is this page?
The grade is for one exact copy of the source (eb0b7f1ffd2c), read on 2026-10-06. The repository is watched and re-audited when it changes.