Jellyseerr MCP Server

Jellyseerr MCP Server

An MCP (Model Context Protocol) server for Jellyseerr that exposes Jellyseerr API functionality as MCP tools usable by LLM clients. It includes colorful, emoji-forward logging and clear console output.

Features

• Exposes key Jellyseerr endpoints as MCP tools (search, request, get request status, etc.)
• Async HTTP client with robust error handling and timeouts
• Colorful, structured logging via Rich with emoji indicators
• Configuration via environment variables (.env supported)

Requirements

• Python 3.10+
• Packages in requirements.txt

Setup

1. Create and activate a virtualenv.
2. pip install -r requirements.txt
3. Copy .env.example to .env and set your values.

Running the MCP server

This server supports stdio (default) and optional HTTP transports.

Stdio (recommended for MCP clients):

You should see colorful logs indicating the server is ready over stdio.

HTTP (SSE) with Bearer token auth (for tools that prefer HTTP + OAuth-style auth):

Then connect your MCP client to http://127.0.0.1:8797 and pass Authorization: Bearer devtoken123.

Exposed tools (initial set)

• search_media(query: str) — Search Jellyseerr for media by query.
• request_media(media_id: int, media_type: str) — Create a media request.
• get_request(request_id: int) — Fetch a request’s details/status.
• ping() — Liveness check with server/transport info.

More tools can be added easily — see jellyseerr_mcp/server.py.

Notes

• The previous FastAPI stub has been replaced with a proper MCP server scaffold.
• HTTP transport (SSE) is available with optional bearer token auth. Full OAuth 2.0 flows require an external issuer or a provider implementation — tell me your preferred OAuth provider and I’ll wire it in.
• The bearer token authentication is a simple implementation and not a full OAuth 2.0 flow. It is suitable for local development or simple deployments until an external issuer is used.