\n\n[](https://github.com/cyanheads/seerr-mcp-server/releases/latest/download/seerr-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=seerr-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvc2VlcnItbWNwLXNlcnZlciJdLCJlbnYiOnsiU0VFUlJfQkFTRV9VUkwiOiJodHRwOi8vbG9jYWxob3N0OjUwNTUiLCJTRUVSUl9BUElfS0VZIjoieW91ci1hcGkta2V5In19) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22seerr-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fseerr-mcp-server%22%5D%2C%22env%22%3A%7B%22SEERR_BASE_URL%22%3A%22http%3A%2F%2Flocalhost%3A5055%22%2C%22SEERR_API_KEY%22%3A%22your-api-key%22%7D%7D)\n\n[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)\n\n
\n\n---\n\nA workflow MCP server over a self-hosted [Jellyseerr](https://github.com/Fallenbagel/jellyseerr) / [Overseerr](https://overseerr.dev/) instance — the request layer that fronts Jellyfin/Plex/Emby plus Radarr and Sonarr. The unit of work is not \"download a movie\"; it is **search → resolve the exact TMDB-backed title → check availability and request state → create a guarded request that Radarr/Sonarr act on.** Jellyseerr owns permissions, quotas, routing, and status; this server never touches Radarr/Sonarr directly.\n\nTwo properties make it safe to hand an agent:\n\n- **Guarded writes.** The one mutating tool (`seerr_request_media`) defaults to `mode: preview` — it resolves the title and returns the exact payload that _would_ be submitted without writing anything. The real request fires only on `mode: request`, which asks for an explicit confirmation and submits only once that confirmation comes back accepted.\n- **Operator-safe output.** Every payload passes through one normalization layer ([`src/services/seerr/normalizers.ts`](./src/services/seerr/normalizers.ts)) that allow-lists the fields it emits, so operator email, Plex/Jellyfin tokens and media-server IDs, and internal `serviceUrl` hosts never reach the model — requesters are projected to `{ id, displayName }`. Redaction is always on; filesystem paths are the single opt-in, behind `includePaths`.\n\n## Tools\n\nSix tools covering the request workflow — discover (`search`) → confirm (`get`) → understand routing (`service_options`) → request (`request_media`) → track (`request_status` / `list_requests`):\n\n| Tool | Description |\n|:---|:---|\n| `seerr_search_media` | Search movies and TV by title; returns ranked matches with TMDB ID, year, overview, and decoded availability when Jellyseerr already tracks the title. The required first step before requesting. |\n| `seerr_get_media` | Fetch exact movie/show details by TMDB ID + media type to confirm the title before a write; for TV, a per-season summary or one season's episode list. |\n| `seerr_list_requests` | List recent requests with status/type/requester filters; echoes the applied filters and decodes every numeric status. Titles are opt-in via `includeTitles`. |\n| `seerr_request_media` | **Guarded write.** Previews the request payload by default (`mode: preview`); creates the request only on `mode: request`, and only after an accepted confirmation. |\n| `seerr_request_status` | Fetch one request by ID — title, decoded request + media availability (incl. 4K), requester, routing summary, and a state-tuned next-step hint. |\n| `seerr_service_options` | Summarize configured Radarr/Sonarr services, default quality profiles, and instance capability flags (4K, partial requests, specials, media server). Filesystem paths redacted unless `includePaths`. |\n\nEvery status field is decoded to `{ raw, label }` — both the numeric code Jellyseerr returns and a human label — so an agent never has to hardcode the enum mapping.\n\n### `seerr_search_media`\n\nTitle disambiguation entry point. Wraps `GET /search`, filters to movies and TV (people are always excluded), and decodes availability when the title is tracked.\n\n- Free-text title queries matched against TMDB; `movie` / `tv` / `all` media-type filter\n- Decoded availability (`status`, plus `status4k` when 4K is enabled) for tracked titles only\n- Pagination by page, with a per-call result `limit` to cap output size\n- Optional ISO 639-1 `language` for localized titles/overviews\n- Empty results are a normal success — returns `[]` with a guidance notice, not an error\n\n---\n\n### `seerr_get_media`\n\nConfirm the exact title before a write. Wraps `GET /movie/{id}` or `GET /tv/{id}`, optionally a season's episodes.\n\n- Availability plus any existing open request for the title (avoids duplicate requests)\n- TV: omit `seasonNumber` for a per-season summary, or pass one to fetch that season's episode list (season 0 is Specials)\n- A TMDB ID that doesn't resolve surfaces as a clean `media_not_found` with a search-recovery hint (Jellyseerr's raw HTTP 500 is classified in the service layer)\n\n---\n\n### `seerr_list_requests`\n\nReview recent requests and their lifecycle. Wraps `GET /request`.\n\n- Lifecycle `filter` (pending, processing, available, failed, …), `mediaType`, and `requestedById` filters\n- Sort by created (`added`) or last-changed (`modified`), ascending or descending\n- `take` / `skip` pagination; the enrichment trailer echoes the filter set the server applied\n- Requester is PII-redacted to `{ id, displayName }`\n- Titles aren't on request objects. `includeTitles: true` joins them from the media records — one lookup per _distinct_ title on the page, so a 4K and a non-4K request for one film cost one call. Default is off, keeping the call to a single upstream read. Rows that can't be resolved keep every other field and are disclosed in the notice\n\n---\n\n### `seerr_request_media`\n\nThe only mutation in the surface, and it is triple-guarded:\n\n1. **`mode: preview` (default)** resolves the title and returns the exact `POST /request` payload that _would_ be submitted — no write. A sloppy call shows the payload and changes nothing.\n2. **`mode: request`** asks for an explicit confirmation and submits only once it comes back accepted. Declining, cancelling, or answering with anything the confirmation schema rejects cancels before submission (`request_cancelled`) — there is no branch that proceeds without an acceptance, so a client that never answers leaves the write un-run.\n3. **`destructiveHint: true`** surfaces the risk in client-side approval flows.\n\nOver HTTP this needs `MCP_SESSION_MODE` to resolve to `stateful` (the default `auto` does): 2025-era clients answer the confirmation over a live session, which `stateless` has no way to hold open.\n\n- Capability validation (4K enabled? seasons valid? partial requests allowed?) runs **locally** against cached instance settings _before_ any POST, so a bad request fails with an actionable typed error instead of a failed write\n- TV requests take `seasons: \"all\"` or an explicit list (e.g. `[1, 2]`); Specials are excluded unless the instance enables them\n- Optional routing overrides (`serverId`, `profileId`, `rootFolder`, `languageProfileId`) — omit to use Jellyseerr's defaults (recommended)\n- An existing request for the title is surfaced in the output; a duplicate rejection from Jellyseerr maps to a typed `duplicate_request` pointing back at it\n\n---\n\n### `seerr_service_options`\n\nLets an agent reason about request capability and routing without a separate status tool. Fans out service + settings + version reads with `Promise.allSettled`, so one failed leg degrades to a disclosed notice rather than failing the call.\n\n- Instance capability summary: Jellyseerr version, media server, and the `movie4kEnabled` / `series4kEnabled` / `partialRequestsEnabled` / `specialEpisodesEnabled` flags\n- Per-service routing: server ID, default-server flag, 4K capability, and the active + available quality profiles (IDs and names, safe to surface)\n- Filesystem root-folder paths and free space are operator-private — omitted unless `includePaths: true`\n\n## Resource and prompt\n\n| Type | Name | Description |\n|:---|:---|:---|\n| Resource | `seerr://request/{requestId}` | Read-once summary of one request — title, decoded status + media availability + routing. Mirrors `seerr_request_status`. |\n\nAll request data is also reachable via tools — request _enumeration_ is the job of `seerr_list_requests` (filterable, the tool-only access path), so the collection is intentionally not exposed as a resource. There are no prompts; the guarded-write workflow lives in the tool, not a prompt template.\n\n## Features\n\nBuilt on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):\n\n- Declarative tool and resource definitions — single file per primitive, framework handles registration and validation\n- Unified error handling — handlers throw, framework catches, classifies, and formats\n- Pluggable auth: `none`, `jwt`, `oauth`\n- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`\n- Structured logging with optional OpenTelemetry tracing\n- STDIO and Streamable HTTP transports\n\nJellyseerr-specific:\n\n- Read + guarded-request only — admin-scope endpoints (approve/decline, retry, edit/delete, media/file deletion, user/settings/sync) are excluded by design, not by API limitation\n- Status decoding centralized in one helper — request and media statuses (including the separate 4K availability) decode to `{ raw, label }` everywhere, forward-compatible with new Jellyseerr status codes\n- Capability validation against cached instance settings catches most bad requests before they reach the API\n- A short-TTL settings cache avoids a round-trip on every preview\n\nAgent-friendly output:\n\n- **Provenance and disclosure** — searches echo the effective query; capped lists disclose truncation; a degraded service leg surfaces a notice instead of silently dropping data\n- **Typed, actionable errors** — `media_not_found`, `request_not_found`, `seasons_required`, `four_k_not_enabled`, `duplicate_request`, and more carry a recovery hint so callers can branch and retry without parsing prose\n\n## Getting started\n\nThis server connects to your own Jellyseerr/Overseerr instance — there is no public hosted endpoint. Add the following to your MCP client configuration file, pointing `SEERR_BASE_URL` at your instance and supplying its API key.\n\n```json\n{\n \"mcpServers\": {\n \"seerr-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"bunx\",\n \"args\": [\"@cyanheads/seerr-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"SEERR_BASE_URL\": \"http://localhost:5055\",\n \"SEERR_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\nOr with npx (no Bun required):\n\n```json\n{\n \"mcpServers\": {\n \"seerr-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@cyanheads/seerr-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"SEERR_BASE_URL\": \"http://localhost:5055\",\n \"SEERR_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\nFor Streamable HTTP, set the transport and start the server:\n\n```sh\nMCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 SEERR_BASE_URL=http://localhost:5055 SEERR_API_KEY=your-api-key bun run start:http\n# Server listens at http://localhost:3010/mcp\n```\n\n### Prerequisites\n\n- [Bun v1.3.2](https://bun.sh/) or higher (or Node.js v24+).\n- A running Jellyseerr or Overseerr instance, and its API key (Settings → General → API Key).\n\n### Installation\n\n1. **Clone the repository:**\n\n```sh\ngit clone https://github.com/cyanheads/seerr-mcp-server.git\n```\n\n2. **Navigate into the directory:**\n\n```sh\ncd seerr-mcp-server\n```\n\n3. **Install dependencies:**\n\n```sh\nbun install\n```\n\n4. **Configure environment:**\n\n```sh\ncp .env.example .env\n# edit .env — set SEERR_BASE_URL and SEERR_API_KEY\n```\n\n## Configuration\n\nAll configuration is validated at startup via Zod schemas in `src/config/server-config.ts`. Key environment variables:\n\n| Variable | Description | Default |\n|:---|:---|:---|\n| `SEERR_BASE_URL` | **Required.** Base URL of the Jellyseerr/Overseerr instance, e.g. `http://localhost:5055`. The service appends `/api/v1` — no `/api/v1` suffix, no trailing slash. | — |\n| `SEERR_API_KEY` | **Required.** Jellyseerr API key (Settings → General → API Key). Sent as the `X-Api-Key` header. | — |\n| `SEERR_REQUEST_TIMEOUT_MS` | Per-request HTTP timeout in milliseconds. | `15000` |\n| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |\n| `MCP_HTTP_PORT` | Port for the HTTP server. | `3010` |\n| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |\n| `MCP_LOG_LEVEL` | Log level (RFC 5424). | `info` |\n| `LOGS_DIR` | Directory for log files (Node.js only). | `/logs` |\n| `STORAGE_PROVIDER_TYPE` | Storage backend. | `in-memory` |\n| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |\n\nSee [`.env.example`](./.env.example) for the full list of optional overrides.\n\n## Running the server\n\n### Local development\n\n- **Build and run:**\n\n ```sh\n # One-time build\n bun run rebuild\n\n # Run the built server\n bun run start:stdio\n # or\n bun run start:http\n ```\n\n- **Run checks and tests:**\n\n ```sh\n bun run devcheck # Lint, format, typecheck, security, changelog sync\n bun run test # Vitest test suite\n bun run lint:mcp # Validate MCP definitions against spec\n ```\n\n### Docker\n\n```sh\ndocker build -t seerr-mcp-server .\ndocker run --rm \\\n -e SEERR_BASE_URL=http://host.docker.internal:5055 \\\n -e SEERR_API_KEY=your-api-key \\\n -p 3010:3010 \\\n seerr-mcp-server\n```\n\nThe Dockerfile defaults to HTTP transport, stateless session mode, and logs to `/var/log/seerr-mcp-server`. OpenTelemetry peer dependencies are installed by default — build with `--build-arg OTEL_ENABLED=false` to omit them.\n\n## Project structure\n\n| Directory | Purpose |\n|:---|:---|\n| `src/index.ts` | `createApp()` entry point — registers the six tools + one resource and inits the Seerr service. |\n| `src/config` | Server-specific environment variable parsing and validation with Zod. |\n| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). |\n| `src/mcp-server/resources` | Resource definitions (`*.resource.ts`). |\n| `src/services/seerr` | Jellyseerr API client, status decoders, and the PII/infra redaction normalizers. |\n| `tests/` | Unit and integration tests mirroring `src/`. |\n\n## Development guide\n\nSee [`CLAUDE.md`/`AGENTS.md`](./CLAUDE.md) for development guidelines and architectural rules. The short version:\n\n- Handlers throw, framework catches — no `try/catch` in tool logic\n- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage\n- Register new tools and resources via the barrels in `src/mcp-server/*/definitions/index.ts`\n- Wrap the Jellyseerr API: validate raw → normalize and redact to a domain type → return the output schema; never fabricate missing fields, and never let operator PII or paths reach output\n\n## Contributing\n\nIssues and pull requests are welcome. Run checks and tests before submitting:\n\n```sh\nbun run devcheck\nbun run test\n```\n\n## License\n\nApache-2.0 — see [LICENSE](LICENSE) for details.\n",
"bytes": 16548,
"sha": "140330a47468c13be67a3ddc95dc66ea046c1bde135a8bd797764afed66518d4",
"repo_slug": "cyanheads/seerr-mcp-server",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_io_github_cyanheads_seerr_mcp_server_58ec505f/readme"
}