Arr-MCP
MCP server to manage your *ARR media stack (Radarr, Sonarr, Lidarr, Readarr, Prowlarr) for searching, adding, and managing movies, TV shows, music, books, and indexers.
README
Arr-MCP
An MCP server for your *ARR stack — Radarr, Sonarr, Lidarr, Readarr, and Prowlarr.
Supports stdio (local, Claude Desktop) and HTTP/Streamable HTTP (remote, ChatGPT, any MCP-compatible client).
Tools
Cross-service
| Tool | Description |
|---|---|
arr_get_services |
Show which services are configured |
arr_search_all |
Search all configured services at once |
Radarr (Movies)
| Tool | Description |
|---|---|
radarr_get_movies |
List movies (paginated) |
radarr_search_movies |
Search by title |
radarr_add_movie |
Add by TMDB ID |
radarr_update_movie |
Update monitored/quality profile |
radarr_delete_movie |
Delete (optionally with files) |
radarr_search_movie |
Trigger download search for a movie |
radarr_refresh_movie |
Refresh metadata |
radarr_get_queue |
Download queue (paginated) |
radarr_delete_queue_item |
Remove item from queue |
radarr_get_calendar |
Upcoming releases |
radarr_get_health |
Health warnings |
radarr_get_quality_profiles |
Quality profiles |
radarr_get_root_folders |
Root folders |
radarr_get_download_clients |
Download clients |
radarr_get_tags |
Tags |
radarr_get_naming |
File naming config |
radarr_get_status |
System status |
Sonarr (TV Shows)
| Tool | Description |
|---|---|
sonarr_get_series |
List series (paginated) |
sonarr_search_series |
Search by title |
sonarr_add_series |
Add by TVDB ID |
sonarr_delete_series |
Delete (optionally with files) |
sonarr_refresh_series |
Refresh metadata |
sonarr_get_episodes |
List episodes (optionally by season) |
sonarr_search_missing |
Trigger search for missing episodes |
sonarr_search_episode |
Trigger search for a specific episode |
sonarr_get_queue |
Download queue (paginated) |
sonarr_delete_queue_item |
Remove item from queue |
sonarr_get_calendar |
Upcoming air dates |
sonarr_get_health |
Health warnings |
sonarr_get_quality_profiles |
Quality profiles |
sonarr_get_root_folders |
Root folders |
sonarr_get_download_clients |
Download clients |
sonarr_get_tags |
Tags |
sonarr_get_naming |
File naming config |
sonarr_get_status |
System status |
Lidarr (Music)
| Tool | Description |
|---|---|
lidarr_get_artists |
List artists (paginated) |
lidarr_search_artists |
Search by name |
lidarr_add_artist |
Add by MusicBrainz ID |
lidarr_get_albums |
List albums (optionally by artist, paginated) |
lidarr_search_missing |
Trigger search for missing albums |
lidarr_get_calendar |
Upcoming album releases |
lidarr_get_health |
Health warnings |
lidarr_get_quality_profiles |
Quality profiles |
lidarr_get_metadata_profiles |
Metadata profiles |
lidarr_get_root_folders |
Root folders |
lidarr_get_download_clients |
Download clients |
lidarr_get_tags |
Tags |
lidarr_get_status |
System status |
Readarr (Books)
| Tool | Description |
|---|---|
readarr_get_authors |
List authors (paginated) |
readarr_search_authors |
Search by name |
readarr_add_author |
Add by Goodreads ID |
readarr_get_books |
List books (optionally by author, paginated) |
readarr_search_books |
Search by title or ISBN |
readarr_get_health |
Health warnings |
readarr_get_quality_profiles |
Quality profiles |
readarr_get_root_folders |
Root folders |
readarr_get_status |
System status |
Prowlarr (Indexers)
| Tool | Description |
|---|---|
prowlarr_get_indexers |
List indexers |
prowlarr_test_indexer |
Test a specific indexer |
prowlarr_test_all_indexers |
Test all indexers |
prowlarr_search |
Search across indexers |
prowlarr_get_indexer_stats |
Indexer statistics |
prowlarr_get_health |
Health warnings |
prowlarr_get_status |
System status |
Setup
1. Install & Build
npm install
npm run build
2. Configure
Copy .env.example to .env and fill in your service URLs and API keys. Only configure the services you use — unconfigured services are skipped at startup and their tools don't appear.
API keys: Settings → General → Security → API Key in each app.
Transport modes
stdio — local (Claude Desktop)
Default mode. The MCP client launches the process directly.
{
"mcpServers": {
"arr": {
"command": "node",
"args": ["/path/to/arr-mcp/dist/index.js"],
"env": {
"RADARR_URL": "http://localhost:7878",
"RADARR_API_KEY": "...",
"SONARR_URL": "http://localhost:8989",
"SONARR_API_KEY": "..."
}
}
}
}
HTTP — remote (ChatGPT, hosted clients)
Set MCP_TRANSPORT=http. The server listens on http://HOST:PORT/mcp and accepts POST requests per the MCP Streamable HTTP spec.
MCP_TRANSPORT=http MCP_PORT=3000 \
RADARR_URL=http://... RADARR_API_KEY=... \
node dist/index.js
A GET /health endpoint is also available for uptime checks.
Docker
Het gepubliceerde image staat op GitHub Container Registry:
ghcr.io/ltmarx/arr-mcp:latest
De docker-compose.yml heeft twee profielen — stdio en http — die nooit tegelijk actief zijn.
HTTP mode — remote/persistent server
cp .env.example .env # vul je keys in
docker compose --profile http up
De server luistert op http://<host>:3000/mcp. Poort aanpassen: MCP_PORT=8080 docker compose --profile http up.
Controleer of de server draait:
curl http://localhost:3000/health
# → {"status":"ok","transport":"http"}
Stdio mode — lokaal (Claude Desktop)
docker compose --profile stdio up
Of direct via docker run (wordt gestart door de MCP client):
docker run --rm -i \
-e RADARR_URL=http://192.168.1.x:7878 \
-e RADARR_API_KEY=abc123 \
ghcr.io/ltmarx/arr-mcp:latest
MCP client config voor Claude Desktop:
{
"mcpServers": {
"arr": {
"command": "docker",
"args": ["run", "--rm", "-i",
"-e", "RADARR_URL", "-e", "RADARR_API_KEY",
"-e", "SONARR_URL", "-e", "SONARR_API_KEY",
"ghcr.io/ltmarx/arr-mcp:latest"
],
"env": {
"RADARR_URL": "http://localhost:7878",
"RADARR_API_KEY": "...",
"SONARR_URL": "http://localhost:8989",
"SONARR_API_KEY": "..."
}
}
}
}
Tip: Als je *ARR draait op de host machine gebruik dan
host.docker.internal(Mac/Windows) of het host IP-adres in plaats vanlocalhost.
Releases
Releases worden automatisch gepubliceerd via GitHub Actions. Maak een tag aan op GitHub (v1.0.0) en publiceer een Release — het multi-arch image (amd64 + arm64) verschijnt vanzelf op GHCR.
Development
npm run dev # run met tsx (geen build stap)
npm run build # compileer naar dist/
npm start # run gecompileerde output
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。