plex-mcp-server
Lets AI assistants browse your libraries, search media, get viewing recommendations, check what's on deck, and more — all read-only against your local Plex instance.
README
plex-mcp-server
MCP server for Plex Media Server. Lets AI assistants browse your libraries, search media, get viewing recommendations, check what's on deck, and more — all read-only against your local Plex instance.
Distributed as a Docker image via GHCR. Designed to run behind mcp-edge-gateway for OAuth-secured remote access.
Tools
Library
get_libraries— list all library sectionsget_library_contents— paginated contents of a section (filter by genre, year, content rating, studio, watched status)get_children— seasons of a show, episodes of a season, tracks of an albumget_media_info— full metadata for any itemget_media_extras— trailers, behind-the-scenes, and other extras
Discovery
search_media— full-text search across all librariesget_genres/get_actors/get_directors— browse by taxonomyget_collections/get_collection_items— named collectionsget_related— Plex's related-content hubs for an itemget_recently_added— new additions across all libraries or a specific sectionget_on_deck— in-progress items with watch percentageget_watch_history— recently watched with timestampsget_random_items— random picks from a section (optionally filtered)
Quick start
docker run --rm \
-e PLEX_URL=http://192.168.1.x:32400 \
-e PLEX_TOKEN=your-token \
-p 3003:3000 \
ghcr.io/x10send/plex-mcp-server:latest
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
PLEX_URL |
Yes | — | Local Plex URL, e.g. http://192.168.1.10:32400 |
PLEX_TOKEN |
No | — | Plex auth token (can be injected per-request by the gateway instead) |
MCP_PORT |
No | 3000 |
Port to listen on |
LOG_LEVEL |
No | info |
debug, info, warn, or error |
PLEX_TOKEN is optional at startup — the server also accepts it per-request via the X-Plex-Token header. The header takes priority over the env var. If neither is present, the server returns 401.
Gateway integration
When running behind mcp-edge-gateway, store your token as PLEX_TOKEN in the gateway's upstream config. The gateway injects it as X-Plex-Token on each request. No token needed in the server's environment.
Development
npm ci
npm run dev # hot-reload dev server
npm run check # format → lint → typecheck → test+coverage → build
npm test # tests only
Coverage thresholds: ≥85% lines/functions, ≥70% branches.
Security
See SECURITY.md. This server is designed for LAN/gateway use only — do not expose it directly to the internet.
License
MIT — see LICENSE.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.