mcp-arr-lite
MCP server for managing media downloads with Radarr and Sonarr, providing granular tools for searching, adding, and grabbing movies and TV shows through natural language.
README
mcp-arr-lite
Lightweight MCP server for Radarr and Sonarr with a small set of granular, purpose-built tools. Unofficial project.
Why this project?
General "arr" MCP servers (like Knuckles-Team/arr-mcp) auto-generate thousands of tools from the Arr API and hand the whole surface to the LLM. mcp-arr-lite is the opposite:
- Granular tools: exactly the operations needed for the "can you grab X for me?" flow — lookup, add, search releases, grab — no admin/config noise.
- Preferred-indexer logic: search tools default to the indexer with the lowest numeric priority, deterministic instead of prompt-dependent.
- HITL-friendly: read-only tools (lookup, list indexers) can be auto-approved; add/search/grab require explicit user approval.
- Dual transport: stdio (npx) and HTTP (Docker).
Comparison with Knuckles-Team/arr-mcp
| Aspect | arr-mcp | mcp-arr-lite |
|---|---|---|
| Tool surface | 1123 generated tools | 9 hand-written tools |
| Preferred indexer | Prompt-dependent | Coded into search tools |
| Apps | 6+ Arr apps | Radarr + Sonarr |
| Transports | stdio | stdio + HTTP |
| Focus | Whole API | Add & download flow |
Tools
| Tool | Read-only | Description |
|---|---|---|
radarr_lookup / sonarr_lookup |
✅ | Search a movie/series by title, returns name + poster URL |
list_indexers |
✅ | List indexers for an app, marking the preferred one |
radarr_add / sonarr_add |
❌ | Add a movie/series (optionally trigger search) |
radarr_search_releases / sonarr_search_releases |
❌ | Search releases, defaulting to the preferred indexer |
radarr_grab / sonarr_grab |
❌ | Start downloading a release |
Requirements
- Node.js >= 20 (npx) or Docker (container)
- Radarr and/or Sonarr with an API key
Installation
Docker Compose (recommended)
services:
arr-mcp:
image: ghcr.io/cuti27/mcp-arr-lite:latest
restart: unless-stopped
environment:
- RADARR_URL=http://radarr:7878
- RADARR_API_KEY=your-radarr-api-key
- SONARR_URL=http://sonarr:8989
- SONARR_API_KEY=your-sonarr-api-key
- MCP_TRANSPORT=http
- MCP_AUTH_TOKEN=your-secure-token-here
- PORT=3000
- HOST=0.0.0.0
- LOG_LEVEL=info
Only configure the apps you use — Radarr and Sonarr are both optional at startup; tools for an unconfigured app will return an error.
stdio (npx)
RADARR_URL=http://radarr:7878 \
RADARR_API_KEY=... \
SONARR_URL=http://sonarr:8989 \
SONARR_API_KEY=... \
MCP_TRANSPORT=stdio \
npx -y @cuti27/mcp-arr-lite
Environment variables
See .env.example. Required per app: RADARR_URL + RADARR_API_KEY, SONARR_URL + SONARR_API_KEY. MCP_AUTH_TOKEN is required when MCP_TRANSPORT=http.
Security
- HTTP transport enforces bearer auth, rate limiting (60 req/min/IP) and a 1 MB body limit.
- API keys are redacted from logs.
- Only run the HTTP transport with
MCP_AUTH_TOKENset and behind a TLS-terminating reverse proxy.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.