dashbrr-mcp
MCP server exposing Dashbrr's REST API as tools, so an LLM can read and manage a dashbrr instance: configured services, per-service health, and summary panels for many apps. Write tools cover settings management, download-queue deletes, Overseerr approvals, UI preferences, and the Plex auth PIN flow.
README
dashbrr-mcp
Part of the arr-mcps collection. MCP server exposing Dashbrr's REST API as tools, so an LLM can read and manage a dashbrr instance: configured services, per-service health, and the summary panels for autobrr, Plex, Jellyfin, Sonarr, Radarr, Lidarr, Readarr, Prowlarr, Overseerr, Traefik, Bazarr, SABnzbd, NZBGet, Uptime Kuma, Maintainerr, and Tailscale. Write tools cover settings management, download-queue deletes, Overseerr approvals, UI preferences, and the Plex auth PIN flow.
Built with FastMCP.
Auth
Dashbrr uses session auth, not an API key. Two ways to use this server:
- Run dashbrr with
DASHBRR_AUTH_BYPASS=true— the API treats any caller as the builtin user. SetDASHBRR_API_KEYto any value (or leave it unset; the server still starts and no auth header is sent). - Obtain a session token (e.g. extract the
dashbrr_user_sessioncookie after logging in to the UI) and setDASHBRR_API_KEYto it — it is sent asAuthorization: Bearer <token>.
Install
Download a wheel from the latest release
and install it as a uv tool (no repo checkout needed):
uv tool install dashbrr_mcp-*.whl
This puts a dashbrr-mcp command on your PATH. Register it with Claude Code:
claude mcp add dashbrr \
--env DASHBRR_URL=https://your-dashbrr-host \
--env DASHBRR_API_KEY=<token-or-empty> \
-- dashbrr-mcp
From source
uv sync
cp .env.example .env # fill in DASHBRR_URL and optionally DASHBRR_API_KEY
claude mcp add dashbrr \
--env DASHBRR_URL=https://your-dashbrr-host \
--env DASHBRR_API_KEY=<token-or-empty> \
-- uv run --directory /path/to/dashbrr-mcp dashbrr-mcp
Config
| Env var | Required | Default |
|---|---|---|
DASHBRR_URL |
yes | - |
DASHBRR_API_KEY |
no | none (no auth header sent; requires DASHBRR_AUTH_BYPASS=true on the instance) |
Tools
5 resource-scoped tools, each covering multiple Dashbrr API endpoints (34
total) via an operation parameter. Grouping here is per-service rather
than per-resource, since Dashbrr's endpoint shape is one summary/action per
third-party service. Call a tool with operation set to one of its listed
operations and an arguments dict matching that operation's parameters — the
tool's own description (visible to your MCP client) lists every operation,
its signature, and a one-line doc. Per-service operations take
instance_id, the type-prefixed instance id from dashbrr_list_settings
(operation dashbrr_list_settings, e.g. sonarr-1, plex-main, autobrr-0).
| Tool | Operations | Covers |
|---|---|---|
dashbrr_other_services |
13 | autobrr, Jellyfin, Uptime Kuma, Maintainerr, Overseerr, Traefik, Bazarr, SABnzbd, NZBGet, Tailscale |
dashbrr_arr_queues |
11 | Sonarr/Radarr/Lidarr/Readarr queues, Prowlarr stats/indexers |
dashbrr_settings |
5 | List/save/delete settings, UI preferences |
dashbrr_plex |
3 | Plex auth pin, sessions |
dashbrr_health |
2 | Liveness probe, per-service health |
Example: dashbrr_arr_queues(operation="dashbrr_delete_sonarr_queue_item", arguments={"instance_id": "sonarr-1", "id": 42}).
Endpoint-level naming is preserved as the operation value:
| Operation | Endpoint |
|---|---|
dashbrr_list_settings |
GET /api/settings |
dashbrr_get_ui_preferences_collapse |
GET /api/ui/preferences/collapse |
dashbrr_get_health |
GET /health |
dashbrr_check_service_health |
GET /api/health/{service} |
dashbrr_get_plex_pin |
GET /api/plex/auth/pin/{pinId} |
dashbrr_get_plex_sessions |
GET /api/plex/sessions |
dashbrr_get_autobrr_stats |
GET /api/autobrr/stats |
dashbrr_get_autobrr_irc |
GET /api/autobrr/irc |
dashbrr_get_autobrr_releases |
GET /api/autobrr/releases |
dashbrr_get_jellyfin_summary |
GET /api/jellyfin/summary |
dashbrr_get_uptimekuma_summary |
GET /api/uptimekuma/summary |
dashbrr_get_maintainerr_collections |
GET /api/maintainerr/collections |
dashbrr_get_overseerr_requests |
GET /api/overseerr/requests |
dashbrr_get_sonarr_queue |
GET /api/sonarr/queue |
dashbrr_get_sonarr_stats |
GET /api/sonarr/stats |
dashbrr_get_radarr_queue |
GET /api/radarr/queue |
dashbrr_get_lidarr_queue |
GET /api/lidarr/queue |
dashbrr_get_readarr_queue |
GET /api/readarr/queue |
dashbrr_get_prowlarr_stats |
GET /api/prowlarr/stats |
dashbrr_get_prowlarr_indexers |
GET /api/prowlarr/indexers |
dashbrr_get_traefik_summary |
GET /api/traefik/summary |
dashbrr_get_bazarr_summary |
GET /api/bazarr/summary |
dashbrr_get_sabnzbd_summary |
GET /api/sabnzbd/summary |
dashbrr_get_nzbget_summary |
GET /api/nzbget/summary |
dashbrr_get_tailscale_devices |
GET /api/tailscale/devices |
dashbrr_create_plex_pin |
POST /api/plex/auth/pin |
dashbrr_delete_sonarr_queue_item |
DELETE /api/sonarr/queue/{id} |
dashbrr_delete_radarr_queue_item |
DELETE /api/radarr/queue/{id} |
dashbrr_delete_lidarr_queue_item |
DELETE /api/lidarr/queue/{id} |
dashbrr_delete_readarr_queue_item |
DELETE /api/readarr/queue/{id} |
dashbrr_set_overseerr_request_status |
POST /api/services/{instanceId}/overseerr/request/{requestId}/{status} |
dashbrr_save_settings |
POST /api/settings/{instance} |
dashbrr_delete_settings |
DELETE /api/settings/{instance} |
dashbrr_set_ui_preference_collapse |
PUT /api/ui/preferences/collapse |
dashbrr_set_overseerr_request_status takes status as the literal string
2 (approve) or 3 (decline). Queue deletes only send options
(remove_from_client, blocklist, skip_redownload, change_category) when
set to true. dashbrr_save_settings omits api_key when blank so the stored
key is retained on update.
Development
make help # list all commands
| Command | Does |
|---|---|
make sync |
uv sync |
make test |
Offline tests - one per endpoint, mocked HTTP |
make test-integration |
Tests against the live instance (needs DASHBRR_URL/DASHBRR_API_KEY) |
make build |
Build wheel + sdist into dist/ |
make bump-patch / bump-minor / bump-major |
Bump the version in pyproject.toml + uv.lock |
make clean |
Remove build artifacts |
The release workflow (.github/workflows/release.yml) builds and publishes to
Releases whenever a v*
tag is pushed - so the usual flow is make bump-patch, commit, then tag and
push.
The integration suite is read-only and never writes to your instance.
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.