Oraclarr

io.github.bdog720Published by GitHub account bdog720v2.0.3Updated Oct 30, 2026

Read-only-by-default MCP server for diagnosing a self-hosted arr stack (Sonarr, Radarr & more).

VerifiedSTDIODesktop onlyCloud & InfrastructureMedia & Design

Overview

AI-generated overview

Read-only-by-default MCP server that lets an assistant diagnose a self-hosted Sonarr/Radarr-style media stack across many services in one place.

What you can do
  • Check stack health, queues, stalls and where a title sits in the pipeline
  • Explain grab decisions, quality profiles, custom formats and history
  • Inspect wanted items, indexers, transcodes, upcoming releases and library status
  • Read host metrics, Docker container state and logs, and running or failed jobs
  • Optionally start a refresh, rescan, search or rename when writes are switched on
When to use it
Useful when you run a self-hosted arr stack (Sonarr, Radarr, Prowlarr, qBittorrent, Jellyfin and similar) and want to ask plain-language operational questions instead of tabbing through several web UIs. Best for troubleshooting downloads, quality decisions, disk and host pressure, and container problems.
Requirements
Runs locally over stdio via uvx (Python 3.12+ and uv), or as a Docker container serving HTTP. Needs a base URL per service instance and credentials: API keys for Sonarr, Radarr and similar services, username and password for qBittorrent. Settings come from ORACLARR_* environment variables or an optional config file; network access to your services is required.
Before you install
It stores API keys and passwords in environment variables or a config file, so keep those out of version control. Writes are off by default; enabling ORACLARR_ALLOW_WRITES plus a per-instance flag lets start_job trigger refreshes, rescans, searches and renames. Over HTTP, writes require ORACLARR_HTTP_TOKEN. Container and log access needs a Docker socket proxy, which grants broad read access to the host.

Installation

In SourceWeft

  1. Open Oraclarr in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Oraclarr

Ask your media stack what's going on, in plain language.

A locally-run MCP server that lets an LLM client (Claude Code, Claude Desktop) diagnose a self-hosted *arr media stack. It only reads by default. Writes are opt-in and need a token.

[License] [Python] [MCP] [Mode] [Status]


What it does

Oraclarr gives a language model one place to answer the operational "why" questions that normally mean tabbing through six web UIs. It aggregates across your services and returns a single, structured answer without changing anything. One opt-in tool, start_job, can start a refresh, rescan, search or rename. See Writes.

Covered now: Sonarr, Radarr, Sportarr, Prowlarr, qBittorrent, Tdarr, Profilarr, Jellyfin, Cleanuparr, Netdata, TrueNAS and Docker, including multiple instances of the same type (a separate anime or 4K Sonarr/Radarr, say). Every tool fans out across all the instances you define and reports each one separately.

In practice

Once connected, you just ask. Oraclarr picks the right tool and answers:

You ask…Oraclarr runs…and tells you
"Is anything in my stack down?"stack_healthwhich services are unreachable, unhealthy, or low on disk, and for one that's down, its container's state and exit code
"Why hasn't the new episode of X downloaded yet?"diagnosewhether X is in your library, sitting in the download queue, or still on the wanted list
"Why did a sub-only release get grabbed when I only allow English dubs?"explain_decisionthe release that was grabbed, its custom-format score, and the language formats that matched
"Why is Cleanuparr about to remove this download?"get_queues + get_cleanupthe strikes against it and their type, whether it's marked for removal, and the rules that apply
"Is the box under I/O pressure, and how much RAM is actually free?"get_hostCPU busy and iowait, I/O pressure, free and available memory, swap, ARC against its max, GPU heat and VRAM
"What errors has Sonarr logged today?"get_containersthe matching log lines with timestamps, from the container's logs
"Is the Sonarr rename still running?"get_jobsrunning and queued commands with their progress and the shows they cover, plus any that failed

Tools

Read-only by default, and outcome-oriented rather than one-per-endpoint, which keeps the model accurate. Only start_job writes, and only when you switch writes on:

ToolAnswers
stack_healthIs anything down / unhealthy / low on disk?
get_queuesUnified active downloads (arr queue ↔ qBittorrent), stalls
diagnoseWhere is X in the pipeline / why isn't it here yet?
explain_decisionWhy was X grabbed or being upgraded? (profile, custom formats, grab history)
get_quality_configQuality profiles, custom formats, release profiles, Profilarr sync state
get_historyRecent grabs / imports / failures
get_wantedWhat's missing / cutoff-unmet?
search_mediaDo I have X, what's its status?
get_indexersWhich indexers are failing?
get_transcodesWhat's transcoding / stuck?
get_upcomingWhat's airing or releasing soon, and will it land? (up to 90 days)
get_libraryJellyfin libraries, scan progress, tasks, playback and transcodes, recent additions, name search
get_cleanupCleanuparr dry-run state, cleaner schedules, seeding and stall rules, strikes
get_hostHost CPU/iowait, memory, swap, ARC, GPU, pools, datasets, disk temperatures, TrueNAS alerts
get_containersDocker containers: state, health, restart counts, exit codes, and a filtered log tail
get_jobsWhat the arrs and Jellyfin are running, queued, failed or scheduled
start_jobStart a refresh, rescan, search or rename on one series or movie, or a Jellyfin scan (opt-in, two-step)

Install

Two ways to run it. Pick one:

  • 🐳 Docker (recommended). A small always-on container next to your arr stack. Works with Dockge, Portainer, Unraid and plain docker compose.
  • 🐍 Python (uv). Runs directly on your machine with no container. Handy for local development, or if you don't use Docker.

Either way, every setting is an environment variable that starts with ORACLARR_. With Docker that means one .env file next to the compose file, and Dockge and Portainer show both in their editors. Start from .env.example. Configuration lists every variable. Your .env is never committed.

Option A: Docker (recommended)

Oraclarr runs as a long-running container that serves MCP over HTTP at http://<host>:7979/mcp. You need two files in one folder: docker-compose.yml and .env.

Using a stack manager (Dockge, Portainer, etc.): create a new stack, paste the compose below into the editor, and paste your settings into the stack's .env. Hit deploy. Portainer saves the variables from its web editor as stack.env, so in Portainer change the compose line to env_file: stack.env.

Using the command line:

bash
cp docker-compose.example.yml docker-compose.ymlcp .env.example .env    # then fill in your URLs and keysdocker compose up -d

This is the whole compose file. You don't edit it when you add or remove a service; that happens in .env:

yaml
services:  oraclarr:    image: ghcr.io/bdog720/oraclarr-mcp:latest    container_name: oraclarr    restart: unless-stopped    ports:      - "7979:7979"           # left side is the host port; change it if 7979 is taken    env_file: .env

Want container state and logs too (get_containers)? Use docker-compose.full.example.yml instead. It adds the read-only Docker socket proxy, the one sidecar that has to live in the same stack. Containers explains it.

Then connect your client: one command for Claude Code, a small JSON block for Claude Desktop, Cursor, Codex, VS Code, Gemini CLI or Windsurf.

Option B: Python (uv)

Run Oraclarr directly, no Docker. Requires Python 3.12+ and uv.

The package is on PyPI as oraclarr-mcp. It speaks MCP over stdio, so your client starts the process and passes the settings in its env block:

json
"oraclarr": {  "command": "uvx",  "args": ["oraclarr-mcp"],  "env": {    "ORACLARR_SONARR_URL": "http://192.168.1.10:8989",    "ORACLARR_SONARR_API_KEY": "your-key",    "ORACLARR_RADARR_URL": "http://192.168.1.10:7878",    "ORACLARR_RADARR_API_KEY": "your-key"  }}

From a clone (for development): put the same ORACLARR_* lines in a .env in the repo folder (it's read at startup), then:

bash
uv syncuv run python -m oraclarr_mcp

In a client config, use "command": "uv", "args": ["run", "python", "-m", "oraclarr_mcp"] and a "cwd" pointing at the repo.

Configuration

Each service is an instance with a name you choose. Its settings are variables named ORACLARR_<NAME>_<FIELD>, and an instance exists as soon as its _URL is set:

ORACLARR_SONARR_URL=http://192.168.1.10:8989ORACLARR_SONARR_API_KEY=your-key
ORACLARR_SONARR_ANIME_TYPE=sonarr           # a second Sonarr, named sonarr-animeORACLARR_SONARR_ANIME_URL=http://192.168.1.10:8990ORACLARR_SONARR_ANIME_API_KEY=your-key
ORACLARR_QBITTORRENT_URL=http://192.168.1.10:8080ORACLARR_QBITTORRENT_USERNAME=adminORACLARR_QBITTORRENT_PASSWORD=your-password
FieldNeeded for
_URLevery instance
_TYPEonly when the name isn't a service type. Types: sonarr, radarr, sportarr, prowlarr, qbittorrent, tdarr, profilarr, jellyfin, cleanuparr, netdata, truenas, docker
_API_KEYSonarr, Radarr, Sportarr, Prowlarr, Profilarr, Jellyfin, Cleanuparr, TrueNAS
_USERNAME, _PASSWORDqBittorrent
_ENABLEDoptional; false switches an instance off without deleting its lines
_VERIFY_TLSoptional; false accepts a self-signed certificate (TrueNAS)
_ALLOW_WRITESoptional; true lets start_job act on this instance. See Writes

Underscores in the name become dashes in the instance name, so SONARR_ANIME shows up as sonarr-anime. Blank values count as unset, so you can keep lines for services you don't run. A misspelled ORACLARR_ variable stops the container with a message that names it, instead of failing quietly later.

Jellyfin needs an API key (Dashboard → API Keys). Cleanuparr needs its account API key (Settings → Account → API Key). TrueNAS, Netdata and Docker each have a short setup guide, linked below.

Server settings are optional:

VariableDefaultWhat it does
ORACLARR_TOOLSETSmedia,downloads,transcode,library,host,containersWhich groups of tools are offered
ORACLARR_TOOL_BUDGET_SECONDS30Time limit per tool call; slow instances report status: "timeout"
ORACLARR_MAX_OUTPUT_BYTES200000Safety net for oversized responses
ORACLARR_TIMEOUT_SECONDS10Timeout for each request to a service
ORACLARR_ALLOW_WRITESfalseTurns on start_job. Each instance also needs its own _ALLOW_WRITES=true
ORACLARR_HTTP_TOKENunsetAt least 24 characters. When set, every HTTP request needs Authorization: Bearer <token>. Required to turn writes on over http

Every tool call has a time budget. If an instance doesn't answer in time, it comes back as status: "timeout" and the other instances still return their data. List results carry only the useful fields and stop at each tool's limit; when there is more, truncated and total say so. API keys and passwords show up as *** in responses and log lines.

Guides

  • Connecting a client: Claude Code, Claude Desktop, Cursor, Codex CLI, VS Code, Gemini CLI and Windsurf, the token header, and why not to use a cloud connector.
  • Host metrics: the TrueNAS read-only user and the Netdata container for get_host.
  • Containers: the Docker socket proxy for get_containers, and what it lets through.
  • Writes: the two switches, the token, the two-step plan flow, and the audit log.
  • The config file: using config.yaml instead of (or as well as) .env, and migrating off it.
  • Upgrading: what to change when you cross a particular version.

Roadmap

Oraclarr is built in phases. It is read-only by default, and write capability arrives behind explicit safety gates. The architecture (typed clients + outcome tools + config-selectable toolsets) is designed to extend to other self-hosted suites beyond *arr, too.

  • ✅ Phase 1: read-only diagnostics. Sonarr, Radarr, Sportarr, Prowlarr, qBittorrent, Tdarr, Profilarr, Jellyfin, Cleanuparr, TrueNAS, Netdata, Docker.
  • 🔜 Phase 2: more services, still read-only. Seerr, Gluetun, Unpackerr, ntfy. The architecture also opens up to non-*arr stacks.
  • 🚧 Phase 3: safe write actions. Started in 2.0.0 with start_job (refresh, rescan, search, rename and Jellyfin scans), gated behind two switches, a token, dry-run previews and an audit log. Retry and request approval come later.
  • 🔭 Phase 4: destructive actions. Delete media, blocklist, stack control and Cleanuparr changes, behind an explicit confirmation and allowlist.

Have a service you'd like covered? Open an issue.

💬 Feedback & Issues

Found a bug or have a feature request? Please open an issue on GitHub.

🤝 Contributing

Issues and PRs welcome. The codebase is TDD throughout:

bash
uv run pytest        # tests (respx-mocked, no live services needed)uv run ruff check .  # lint

Adding a service follows a small recipe (new client → register by type → extend a tool → write the test). See the project layout under src/oraclarr_mcp/.

📄 License

Apache License 2.0. See LICENSE.

💖 Support the Project

If Oraclarr saves you from tabbing through six web UIs to work out why something didn't download, consider buying me a coffee.

[Buy Me A Coffee]

Source: README.md at commit e3d1014

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package did not install.

Version history

6
  1. v2.0.3LatestOct 30, 2026
  2. v2.0.2Oct 13, 2026
  3. v1.7.0Oct 13, 2026
  4. v1.6.0Oct 12, 2026
  5. v1.3.0Oct 12, 2026
  6. v1.0.1Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts