Skip to main content
Glama

An MCP server to query, troubleshoot and manage Sonarr, Radarr and Prowlarr from Claude Desktop or any other MCP client.

It focuses on the questions that come up most often in the Sonarr and Radarr issues and wiki:

  • "Why didn't it grab S03E04? Which releases are out there and why were they rejected?"

  • "Why isn't this download importing?"

  • "Which downloads are stalled? Remove them and find another release."

  • "Would this release be an upgrade over my file? Why does it say 'not an upgrade'?"

  • "Remove the .exe releases from the queue, blocklist them and search again."

  • "Which indexer failed the most this month?"

  • "Add Severance with the HD-1080p profile."

Status: v0.2.0. 43 tools, 269 tests. Validated against a real Sonarr, Radarr and Prowlarr on a Synology NAS, and every tool (including writes) against disposable Sonarr/Radarr/Prowlarr containers. See Status.

Features

  • 42 tools in seven groups: status, library, diagnostics, troubleshooting, maintenance, actions and Prowlarr. Full reference in docs/TOOLS.md.

  • Guided troubleshooting:

    • explain_search runs an interactive search and groups the releases by rejection reason (language, size, quality, custom format score…).

    • diagnose_import and check_paths give the probable cause of a failed import and how to fix it: remote path mapping, permissions, manual match, "not an upgrade"…

    • find_stalled_downloads spots stuck downloads.

    • parse_release shows how a release is scored and estimates whether it would be an upgrade.

    • get_health adds the usual fix to each known health warning; test_download_clients tests the download clients.

  • Maintenance: bulk_edit_preview / bulk_edit_apply change many series/movies at once (monitoring, quality profile, tags…), always with a preview first; preview_rename / rename_files rename with a preview; library_report shows what takes space and what could be cleaned up.

  • Follows Sonarr/Radarr good practice, enforced in code: an hourly indexer budget, no repeated searches, mass searches and removals in two steps, imports that never break seeding or replace files without permission, and previews before bulk changes. See docs/GOOD_PRACTICES.md.

  • Compact answers. Never returns raw API JSON: overviews are trimmed, images and internal fields are dropped, and lists are paged with limit and truncated.

  • Readable errors in English or Spanish (ARR_LANG). For example, "Sonarr returned 401: wrong API key (check SONARR_API_KEY)" instead of a traceback.

  • Titles or IDs. Tools accept "The Capture", "Dune 2021" or 42. When a title is ambiguous they return the candidates instead of guessing.

  • Partial failures are tolerated. If Radarr is down, get_queue still shows Sonarr's queue and flags Radarr's error.

  • Read-only mode (ARR_READONLY=true): write tools are not even registered.

  • Safe imports. manual_import only imports files listed one by one, never imports two files for the same episode, and imports nothing if anything is wrong. Unidentified files can be matched by hand; Sonarr/Radarr re-validate the match before importing.

  • Fake releases (.exe .scr .lnk .bat .cmd .msi .zipx) and orphaned downloads (files left in the download folder that nothing is tracking).

Related MCP server: media-stack-mcp

Requirements

  • Windows or Linux (tested in CI on both, Python 3.11–3.13; macOS should work but is not tested).

  • Python ≥ 3.11

  • Sonarr v4 and/or Radarr v5–v6 (/api/v3). Tested with Sonarr 4.0.16 and 4.0.20, Radarr 5.28, 6.2 and 6.4.4. Prowlarr (/api/v1, tested with 2.4.0 and 2.6.5) is optional.

  • The API key of each service (in each app: Settings → General → Security → API Key).

Installation

Quickest: with uv (no Git, no manual Python setup)

uv downloads Python by itself and runs arr-doctor straight from the latest release.

  1. Install uv once:

    • Windows (PowerShell): powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

    • Linux / macOS: curl -LsSf https://astral.sh/uv/install.sh | sh

  2. In Claude Desktop (Settings → Developer → Edit Config), add inside mcpServers:

    "arr": {
      "command": "uvx",
      "args": ["--from", "https://github.com/alexliam83/arr-doctor/releases/download/v0.2.0/arr_doctor-0.2.0-py3-none-any.whl", "arr-doctor"],
      "env": {
        "SONARR_URL": "http://192.168.1.10:8989",
        "SONARR_API_KEY": "your-sonarr-api-key",
        "RADARR_URL": "http://192.168.1.10:7878",
        "RADARR_API_KEY": "your-radarr-api-key"
      }
    }

    If Claude Desktop cannot find uvx, put its full path in command, e.g. "command": "C:\\Users\\<you>\\.local\\bin\\uvx.exe" on Windows or "~/.local/bin/uvx" elsewhere.

  3. Restart Claude Desktop completely.

Without uv: pip install https://github.com/alexliam83/arr-doctor/releases/download/v0.2.0/arr_doctor-0.2.0-py3-none-any.whl installs the arr-doctor command.

From source (Windows, Claude Desktop)

cd C:\
git clone https://github.com/alexliam83/arr-doctor.git
cd arr-doctor
python -m venv .venv
.\.venv\Scripts\pip install -e .

In Claude Desktop, open Settings → Developer → Edit Config and add this inside mcpServers, leaving the rest of the file alone:

"arr": {
  "command": "C:\\arr-doctor\\.venv\\Scripts\\arr-doctor.exe",
  "env": {
    "SONARR_URL": "http://192.168.1.10:8989",
    "SONARR_API_KEY": "your-sonarr-api-key",
    "RADARR_URL": "http://192.168.1.10:7878",
    "RADARR_API_KEY": "your-radarr-api-key"
  }
}

If the file was empty, it ends up like this:

{
  "mcpServers": {
    "arr": { "command": "…", "env": { "…": "…" } }
  }
}

Restart Claude Desktop completely, quitting it from the system tray icon too. In a new conversation, the tools icon should list arr.

Claude Desktop from the Microsoft Store. This version keeps its config in a virtualized path, usually %LOCALAPPDATA%\Packages\Claude_…\LocalCache\Roaming\Claude\claude_desktop_config.json. Always open it with "Edit Config" to be sure you edit the right file. Server logs are in the logs folder of that same directory (mcp-server-arr.log).

Linux / macOS

git clone https://github.com/alexliam83/arr-doctor.git && cd arr-doctor
python3 -m venv .venv
.venv/bin/pip install -e .
cp .env.example .env   # and fill in the keys

In your MCP client config, use /path/to/arr-doctor/.venv/bin/arr-doctor as the command.

Configuration

Variables are read from the environment (the env block of the MCP client) or from a .env file in the repository folder. There is a template in .env.example.

Variable

Required

Default

Description

SONARR_URL

yes*

—

Full URL, e.g. http://192.168.1.10:8989

SONARR_API_KEY

yes*

—

RADARR_URL

yes*

—

e.g. http://192.168.1.10:7878

RADARR_API_KEY

yes*

—

PROWLARR_URL

no

—

e.g. http://192.168.1.10:9696

PROWLARR_API_KEY

no

—

ARR_LANG

no

en

Language of errors and notes: en or es

ARR_READONLY

no

false

true disables every write tool

ARR_INDEXER_BUDGET_PER_HOUR

no

30

Max searches/grabs/indexer tests per hour (0 = unlimited)

ARR_SEARCH_CONFIRM_ABOVE

no

10

Searches or queue removals over this many items need confirmation

ARR_SEARCH_COOLDOWN_MINUTES

no

60

Skip items searched less than this many minutes ago (0 = off)

ARR_TIMEOUT

no

15

HTTP timeout in seconds. Scans and interactive searches use higher values

ARR_DOWNLOADS_PATH

no

auto

Download folder as Sonarr/Radarr see it, used by find_orphan_downloads. If unset, it is detected from the queue and the import history

* At least Sonarr or Radarr is required. A service without both a URL and an API key is not registered, so its tools do not appear. Full URLs are used so reverse proxies and HTTPS work.

Docker / NAS. If the port is assigned automatically (for example, Synology Container Manager in auto mode), it may change when the container is recreated. If get_system_status cannot connect, check the port, or better, pin it.

API keys never go into the repository. .env is in .gitignore.

Usage

Typical conversations and the tools Claude usually picks:

Question

Tools

"Why didn't it grab S03E04?"

explain_search → grab_release if you want a rejected one

"Why isn't it importing?"

diagnose_import → check_paths → manual_import(matches=…)

"Which downloads are stalled?"

find_stalled_downloads → remove_from_queue(blocklist=true)

"Would this release be an upgrade?"

parse_release

"What's stuck in the queue?"

get_queue(only_problems=true)

"Remove the .exe releases and search again"

find_suspicious_releases → remove_from_queue(blocklist=true)

"Which indexer fails the most this month?"

get_indexer_stats(days=30)

"What takes the most space?"

library_report

"Unmonitor every ended series that is complete"

bulk_edit_preview → bulk_edit_apply

"Which files don't follow my naming scheme?"

preview_rename → rename_files

"Add Severance in HD-1080p"

add_series (if profile or root folder are missing, it returns the options)

"Import what was left in downloads"

find_orphan_downloads → manual_import(files=[…])

Searches, refreshes and imports are asynchronous commands in Sonarr/Radarr. The tool returns a command_id you can follow with get_command_status.

explain_search queries every indexer live (it is the same interactive search as the web UI). Use it for a specific episode or movie, not in a loop.

Tools that change or delete things

  • remove_from_queue: removes queue items. By default it also removes the task from the download client (remove_from_client=true). With blocklist=true the release is blocklisted and, unless skip_redownload=true, Sonarr/Radarr automatically search for another one.

  • manual_import: imports specific files into the library. By default (import_mode="auto") it copies/hardlinks while the download is seeding and moves otherwise. Replacing a file already in the library needs allow_replace=true.

  • grab_release: sends a specific release to the download client even if it was rejected.

  • bulk_edit_apply: changes many items at once; for several items it needs the token from bulk_edit_preview.

  • rename_files: renames files on disk to match the naming settings.

Claude Desktop asks for permission the first time each tool is used. For these it is better not to choose "Always allow", so you can review each call. The two that delete also carry the MCP destructiveHint annotation.

Development

python -m venv .venv
.venv/bin/pip install -e ".[dev]"        # Windows: .venv\Scripts\pip
.venv/bin/pytest                          # unit tests with respx (no network)
uvx ruff check arr_doctor tests scripts      # lint
python scripts/gen_tools_doc.py           # regenerates docs/TOOLS.md and docs/TOOLS.es.md (a test checks they are up to date)

Against a real server (read-only, uses .env):

python scripts/smoke.py              # calls every read-only tool and prints a summary
python scripts/smoke.py --verbose    # also prints each answer
python scripts/smoke.py --capture    # saves anonymized raw responses to scripts/captures/ (git-ignored)

smoke.py refuses to call any tool that is not annotated readOnlyHint, and skips explain_search because it queries the indexers.

In Claude Desktop: a manual checklist (does the model pick the right tools, respect confirmations, explain results?) is in docs/testing/claude-desktop.md.

MCP Inspector:

npx @modelcontextprotocol/inspector .venv/bin/python -m arr_doctor.server          # web UI
npx @modelcontextprotocol/inspector --cli .venv/bin/arr-doctor -e SONARR_URL=… -e SONARR_API_KEY=… --method tools/list

On Windows, replace .venv/bin/python with .venv/Scripts/python.exe.

Layout

arr_doctor/
├── server.py         # FastMCP, conditional tool registration, main()
├── config.py         # Settings (pydantic-settings)
├── i18n.py           # English and Spanish messages
├── paths.py          # comparing POSIX / Windows / UNC paths from Sonarr/Radarr
├── formatting.py     # compacting API responses
├── clients/          # HTTP: base.py (errors, X-Api-Key), sonarr.py, radarr.py, prowlarr.py
└── tools/            # library, diagnostics, troubleshoot, maintenance, actions, indexers, common
tests/                # pytest + respx; fixtures/ with sample responses
scripts/              # smoke.py, gen_tools_doc.py
docs/                 # TOOLS (generated), DESIGN, ROADMAP — in English and Spanish

Status

All tools have unit tests (mocked HTTP) and the server has an end-to-end stdio test. On top of that, they were run against a real Sonarr 4.0.16 and Radarr 6.2 on a Synology NAS (real library, read-only plus a few approved changes) and against disposable Docker containers of Sonarr 4.0.20, Radarr 5.28 and 6.4.4, and Prowlarr 2.6.5 (empty libraries, every tool including writes):

Block

Real NAS

Containers

Notes

Skeleton, get_system_status

✅

✅

stdio, MCP Inspector, readable errors

Library and diagnostics (read-only)

✅

✅

Every tool, Sonarr and Radarr

Troubleshooting (read-only)

✅

✅

On the NAS it found a real fake .exe, stalled downloads and orphaned files. explain_search ran in containers only (no indexers there)

Write actions

✅ partly

✅

NAS: refresh_item, remove_from_queue with blocklist, manual_import (6 episodes). Containers: add_series/add_movie, set_monitored, all searches. grab_release only mocked (needs real indexers)

Maintenance

✅ partly

✅

NAS: library_report, preview_rename. Containers: bulk_edit_preview / bulk_edit_apply, test_download_clients. rename_files apply only mocked (needs files on disk)

Prowlarr

✅

✅

NAS (Prowlarr 2.4.0, 11 indexers): every tool, including test_indexers and set_indexer_enabled (8 dead indexers disabled; credentials untouched)

Windows and Linux

✅

—

CI on both + a real Windows machine

Good-practice guardrails

✅

✅

Roadmap low priority

—

—

Not started

Testing against the real server found and fixed several issues mocks could not show (unknown queue items, stalled-download cases, imports reported as successful that had failed, long imports vs. client timeouts). The fixtures in tests/fixtures/ still use made-up data shaped like the official OpenAPI schemas; they can be replaced with anonymized real responses (smoke.py --capture).

Credits and license

Created by Alexliam (@alexliam).

Inspired by BerryKuipers/mcp_services_radarr_sonarr. This is a new implementation that does not reuse its code.

MIT license.

Available Tools

36 tools
add_seriesA

Add a new series to Sonarr. Looks it up online first; if several results match it returns the candidates, and if quality profile or root folder are missing it returns the available options instead of guessing.

Examples: "Add The Capture with the HD-1080p profile", "Add Severance and search for it"

Inputs: term (required), monitor, tvdb_id, search_now, +2 more. Returns: object

bulk_edit_applyA

Apply a change to many series or movies at once. For several items or a filter selection, call bulk_edit_preview first, show it to the user and only call this once they agree, passing the preview's confirmation_token (same selection and changes). A single item named by the user can be changed directly. Root folders are not changed here because that would move files.

Examples: "Yes, unmonitor those ended series", "Tag The Capture with 'uk'"

Inputs: service (required), tag, items, status, +12 more. Returns: object

bulk_edit_previewA
Read-only

Preview a change to many series or movies at once (monitoring, quality profile, tags, series type, minimum availability): which items match and what would change. Changes nothing. Select items by IDs/titles and/or filters (status, monitored, quality profile, tag, year, complete). Show the preview to the user; if they agree, apply it with bulk_edit_apply and the confirmation_token returned here.

Examples: "Which ended series would be unmonitored?", "Preview putting the 4K profile on all 2024 movies"

Inputs: service (required), tag, items, status, +11 more. Returns: object

check_pathsA
Read-only

Check the path setup that breaks most imports: root folders (accessible, free space), remote path mappings, download clients, whether Sonarr/Radarr can actually see the download clients' output folders, and the related health warnings.

Examples: "Is my remote path mapping right?", "Why does Sonarr say the path does not exist?"

Inputs: service. Returns: object

diagnose_importA
Read-only

Diagnose why a download is not being imported: combines the queue status messages, Sonarr/Radarr's own rejections for the files in the download, and path visibility, and returns the probable cause with a concrete fix (remote path mapping, permissions, manual match, not an upgrade, sample, fake release…).

Examples: "Why isn't S03E04 importing?", "Why is everything stuck in importBlocked?"

Inputs: service (required), queue_id. Returns: object

find_orphan_downloadsA
Read-only

Importable files in the downloads folder that no queue item is tracking (e.g. Download Station removed the task before Sonarr imported it). Groups them by series/movie and says whether each episode/movie already has a file (duplicate) or is missing. Also flags several files for the same episode. If no folder is configured, the download folders are detected from the queue and the import history. The scan can take a while on a NAS.

Examples: "Why wasn't S03E04 of The Capture imported?", "Is anything stuck in /downloads?"

Inputs: limit, folder, service. Returns: object

find_stalled_downloadsA
Read-only

Find downloads that are stuck: reported as stalled / no connections / no seeds by the download client, with a download client error, or — after min_hours — still at 0 % (no_progress), downloading with no speed/ETA (no_activity), or with no metadata yet (size 0, typical of magnets without peers). Paused or queued items are not reported. Pair with remove_from_queue(blocklist=true) to grab a different release.

Examples: "Which downloads are stalled?", "Remove the stuck torrents and find another release"

Inputs: service, min_hours. Returns: object

find_suspicious_releasesA
Read-only

Detect fake/malicious releases, with the indexer that provided them: executables (.exe .scr .lnk .bat .cmd .msi .zipx) in the queue, history and blocklist; grabs made more than a day before the episode aired or the movie's digital/physical release (likely="fake" if they never imported, "early_release" if they did, e.g. box sets); and different downloads for different episodes with the exact same size.

Examples: "Is there any .exe in the queue?", "Which indexer is sending me fake releases?"

Inputs: days, service. Returns: object

get_blocklistA
Read-only

Blocklisted releases with the indexer they came from and the reason.

Examples: "What's in the blocklist?", "Which indexer has the most blocklisted releases?"

Inputs: limit, service. Returns: object

get_calendarA
Read-only

Upcoming (or recent) episode air dates and movie releases.

Examples: "What airs this week?", "What came out in the last 3 days?"

Inputs: limit, service, days_back, days_ahead, +1 more. Returns: object

get_command_statusA
Read-only

Status of an asynchronous command (search, refresh, manual import) started earlier. For a finished manual import it also checks that each file really reached the library.

Examples: "Has the search for S03E04 finished?", "Did the manual import work?"

Inputs: service (required), command_id (required). Returns: object

get_cutoff_unmetB
Read-only

Items that have a file but below the quality profile cutoff (upgrade candidates).

Examples: "What could be upgraded to better quality?", "Which movies are below cutoff?"

Inputs: limit, service, monitored_only. Returns: object

get_disk_spaceA
Read-only

Free and total space of the disks/volumes seen by Sonarr/Radarr.

Examples: "How much disk space is left on the NAS?"

Inputs: service. Returns: object

get_episodesA
Read-only

Episodes of a series with has_file, monitored, air date and file quality.

Examples: "Is S03E04 of The Capture downloaded?", "Which episodes of season 2 are missing?"

Inputs: series (required), limit, season, only_missing. Returns: object

get_healthA
Read-only

Health warnings and errors reported by Sonarr/Radarr (and Prowlarr if configured): unreachable download client, missing root folder, indexers failing… each with the usual fix when it is a known check.

Examples: "Any health warnings?", "Is something wrong with Radarr?"

Inputs: service. Returns: object

get_historyA
Read-only

Activity history: grabs (with indexer), imports, failed downloads, deletions.

Examples: "Which indexer did S03E04 of The Capture come from?", "What failed to download in the last 7 days?"

Inputs: days, limit, movie, series, +2 more. Returns: object

get_logsA
Read-only

Latest log entries at the given level (default: errors).

Examples: "Show me Sonarr's recent errors", "Why is Radarr failing? check the logs"

Inputs: level, limit, service. Returns: object

get_missingA
Read-only

Wanted/missing: monitored episodes (Sonarr) or movies (Radarr) without a file.

Examples: "What episodes am I missing?", "Which movies are still not downloaded?"

Inputs: limit, service, monitored_only. Returns: object

get_queueA
Read-only

Download queue with tracked state (downloading, importBlocked, importPending, failed…), status messages explaining why an import is stuck, indexer and download client. Downloads that Sonarr/Radarr did not grab themselves are hidden (as in the web UI) and only counted, unless include_unknown=true. Stalled downloads (no activity, no metadata, no progress for 6 h) are marked with stall_reason and count as problems, even when Sonarr/Radarr report them as healthy.

Examples: "What's stuck in the queue and why?", "Is S03E04 of The Capture still downloading?"

Inputs: limit, service, only_problems, include_unknown. Returns: object

get_seriesA
Read-only

Details of one series in Sonarr, including per-season statistics (episodes on disk vs aired, monitored seasons, size).

Examples: "How complete is The Capture?", "Which seasons of Severance are monitored?"

Inputs: series (required). Returns: object

get_system_statusA
Read-only

Version and reachability of every configured service (Sonarr, Radarr, Prowlarr).

Use it first when something fails, to check connectivity and API keys. Examples: "Are Sonarr and Radarr up?", "Which Radarr version am I running?"

Inputs: no named parameters. Returns: object

grab_releaseA

Send a specific release (from explain_search) to the download client, even if it was rejected. Only works within ~30 minutes of the search; search again if it fails.

Examples: "Grab that 1080p release anyway", "Download the second one from the list"

Inputs: guid (required), service (required), indexer_id (required). Returns: object

library_reportB
Read-only

Disk usage and cleanup report: total size, biggest series/movies, unmonitored items that still have files, ended series that are complete, size per quality (movies) and free space per root folder. Read-only: it never deletes anything.

Examples: "What takes the most space?", "What could I delete to free space?"

Inputs: limit, service. Returns: object

manual_importA
Destructive

Import specific files from the downloads folder into the library (all or nothing). Never imports a whole folder blindly: every file must be listed, must be matched to a series/episode or movie, must have no rejections, and no two files may target the same episode or movie. If anything fails, nothing is imported and the problems are returned. When Sonarr/Radarr cannot identify a file ("Unknown Series", "matched by ID, manual import required"), pass matches to assign it by hand; the assignment is re-validated first. Replacing a file that is already in the library needs allow_replace=true. By default it waits for the import and verifies each file (Sonarr/Radarr report the command as successful even when a file fails to move), returning the reason from their log for any file that did not get in.

Examples: "Import /downloads/The.Capture.S03E04.1080p.mkv", "Import that file as episode 4 of season 3 of The Capture"

Inputs: files (required), service (required), wait, matches, +3 more. Returns: object

parse_releaseA
Read-only

Show how Sonarr/Radarr interpret a release name: matched series/episodes or movie, quality, languages, custom formats and score. If the item already has a file, compares both and estimates whether it would be an upgrade under the quality profile and why.

Examples: "How would Sonarr score 'The.Capture.S03E04.2160p.WEB.DV-GRP'?", "Why is this release 'not an upgrade'?"

Inputs: title (required), service. Returns: object

preview_renameA
Read-only

Preview which files would be renamed by the current naming settings (current path -> new path). Nothing is changed. Show it to the user; if they agree, apply with rename_files and the confirmation_token returned here.

Examples: "Which files of The Capture don't follow my naming scheme?", "Preview renaming Dune"

Inputs: limit, movie, season, series. Returns: object

refresh_itemA

Refresh metadata and rescan files on disk for a series or movie.

Examples: "Refresh The Capture", "Rescan the files of Dune"

Inputs: movie, series. Returns: object

remove_from_queueA
Destructive

Remove items from the download queue, optionally deleting them from the download client and blocklisting the release. With blocklist=true and skip_redownload=false, Sonarr/Radarr automatically search for another release. Removing a torrent from the client stops seeding (private trackers may count it as hit-and-run). Many items at once need confirm=true.

Examples: "Remove the .exe releases from the queue, blocklist them and find another version", "Delete queue item 42 from Download Station"

Inputs: service (required), queue_ids (required), confirm, blocklist, +2 more. Returns: object

rename_filesA

Rename the files of a series (optionally one season) or a movie to match the current naming settings. Call preview_rename first, show it to the user and only call this once they agree, passing the preview's confirmation_token (required for more than one file).

Examples: "Yes, rename the files of The Capture season 3", "Apply the rename to Dune"

Inputs: movie, season, series, confirmation_token. Returns: object

search_episodesA

Trigger an indexer search for specific episodes (by ID, or series + season + episode numbers). Episodes searched in the last hour are skipped (force=true to override) and searches over many episodes ask for confirmation first, to respect indexer limits.

Examples: "Search S03E04 of The Capture again", "Look for episodes 3 and 4 of season 1 of Severance"

Inputs: force, season, series, confirm, +2 more. Returns: object

search_libraryA
Read-only

Search the local Sonarr/Radarr library (what is already added) by title.

Does not search the internet; use add_series/add_movie for that. Examples: "Do I have The Capture?", "Which Star Wars movies are in my library?"

Inputs: limit, query, service. Returns: object

search_missingA

Trigger a search for every monitored missing episode (Sonarr) and/or movie (Radarr). Sonarr/Radarr normally find new releases through RSS on their own; mass searches hit every indexer once per item and can exceed indexer limits. Over a few items it first returns how many would be searched and needs confirm=true. Prefer narrower searches.

Examples: "Search everything that's missing", "Search all missing episodes of The Capture"

Inputs: series, confirm, service. Returns: object

search_seasonA

Trigger an indexer search for a whole season (season packs or every episode).

Examples: "Search season 2 of The Capture"

Inputs: season (required), series (required). Returns: object

set_monitoredA
Idempotent

Monitor or unmonitor episodes (by ID, or series + season + episode numbers in one call), a whole season, a whole series, or a movie.

Examples: "Stop monitoring S03E02 of Lioness", "Stop monitoring season 1 of The Capture", "Unmonitor the movie Cats"

Inputs: monitored (required), movie, season, series, +2 more. Returns: object

test_download_clientsA
Read-only

Test the connection to every download client configured in Sonarr/Radarr and report which ones fail and why.

Examples: "Can Sonarr reach my download client?", "Test the download clients"

Inputs: service. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 36 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes and detailed descriptions help differentiate (e.g., parse_release vs explain_search vs grab_release). However, several diagnostic tools overlap: find_stalled_downloads vs get_queue's stall detection, check_paths vs get_health, and library_report vs get_disk_space, creating some risk of misselection.

    Naming Consistency4/5

    Almost all tools use snake_case with consistent verb_noun patterns (get_queue, search_episodes, add_series). Minor deviations like library_report (noun_report) and manual_import (adjective_noun) are readable but slightly break the convention.

    Tool Count2/5

    36 tools far exceeds the typical 3-15 well-scoped range and surpasses the 25+ threshold for 'too many'. While the domain is broad, many tools could be consolidated or scoped down without losing core functionality.

    Completeness3/5

    The surface is extensive for diagnostics and many management tasks (queue, history, health, imports, renaming, bulk edits). But notable gaps exist: no add_movie tool despite Radarr support, and no way to delete a series/movie from the library, which can block common lifecycle operations.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables interaction with the *arr media management suite (Sonarr, Radarr, Lidarr, Prowlarr, SABnzbd) and TRaSH Guides through MCP tools, allowing media library management, searching, and configuration via natural language.
      70
      16 npm
      1
      MIT
    • A
      license
      C
      quality
      B
      maintenance
      Enables full control of Sonarr from Claude.ai and Claude Code by exposing all 234 v3 API operations as tools for managing media libraries.
      235
      23 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables Claude Desktop to troubleshoot and manage a self-hosted Plex + Servarr media stack, including diagnosing missing media, monitoring download queues and indexer health, and coordinating operational tasks across Radarr, Sonarr, SABnzbd, qBittorrent, Tautulli, TMDb, Prowlarr, and remote hosts.
      26
      MIT