Yarr MCP Server

Rust MCP and CLI server for Sonarr, Radarr, Prowlarr, Plex, Jellyfin, and download clients.

Remote serverstreamable-http

What is the Yarr MCP MCP server?

Connect Yarr MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Rust MCP and CLI server for Sonarr, Radarr, Prowlarr, Plex, Jellyfin, and download clients. The yarr mcp mcp server is what makes that connection.

What the server does

MCP server and CLI for self-hosted media fleets: Sonarr, Radarr, Prowlarr, Bazarr, Tautulli, Overseerr, SABnzbd, qBittorrent, Plex, Jellyfin, and Tracearr.

  • Fleet status checks across the configured services
  • Credentialed upstream API passthrough for known service kinds
  • Table-driven OpenAPI operation metadata for Sonarr, Radarr, Prowlarr,
  • Curated commands for SABnzbd, qBittorrent, Tautulli, Bazarr, and Tracearr,
  • Code Mode over MCP for multi-step media automation scripts
  • Snippet storage and execution for repeatable Code Mode workflows

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • stdio — stdio is the preferred local MCP transport. It starts yarr mcp on demand and does not require binding a local HTTP port

Credentials and setup notes

Configuration is passed through the environment: YARR_SERVICES, YARR_SONARR_URL, YARR_SONARR_API_KEY, RUST_LOG, YARR_MCP_TOKEN, YARR_MCP_HOST, YARR_RADARR_URL, YARR_RADARR_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Yarr MCP's toolset — stdio — is a fair guide to whether it matches your workflow. It is maintained by ai.dinglebear; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
stdiostdio is the preferred local MCP transport. It starts yarr mcp on demand and does not require binding a local HTTP port.

How to install the Yarr MCP MCP server

```json
{
  "mcpServers": {
    "yarr": {
      "url": "http://127.0.0.1:40070/mcp",
      "headers": {
        "Authorization": "Bearer ${YARR_MCP_TOKEN}"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
YARR_SERVICESConfiguration value read at startup.Optional
YARR_SONARR_URLEndpoint or connection string the server talks to.Yes
YARR_SONARR_API_KEYCredential the server authenticates with.Yes
RUST_LOGConfiguration value read at startup.Optional
YARR_MCP_TOKENCredential the server authenticates with.Yes
YARR_MCP_HOSTEndpoint or connection string the server talks to.Optional
YARR_RADARR_URLEndpoint or connection string the server talks to.Yes
YARR_RADARR_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Yarr MCP to stdio.

Frequently asked questions

It connects Yarr MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (stdio) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Yarr MCP directly.