mcp-plex
MCP server for Plex Media Server, focused on media discovery, search, library management, and playback control.
README
mcp-plex
MCP server for Plex Media Server, focused on media discovery, search, library management, and playback control. 24 granular tools designed for use with Claude and other LLM agents.
Prerequisites
- Python 3.14+
- uv
- A running Plex Media Server
- A Plex authentication token
Setup
1. Get Your Plex Token
The easiest way to find your Plex token:
- Sign in to Plex Web App
- Browse to any media item and click Get Info (or ... > Get Info)
- Click View XML in the bottom-left
- In the URL bar, find the
X-Plex-Token=parameter -- that's your token
Alternatively, check the Plex support article for other methods.
2. Install
cd mcp-plex
uv sync
3. Configure Environment Variables
Set these before running the server:
export PLEX_SERVER_URL="http://your-plex-server:32400"
export PLEX_TOKEN="your_plex_token"
4. Test the Connection
uv run mcp-plex-server
The server connects to your Plex server on startup and verifies the token. If the connection fails, check that your server URL and token are correct.
Claude Desktop / Claude Code Configuration
Add to your MCP server config. If installed from PyPI:
{
"mcpServers": {
"plex": {
"command": "uvx",
"args": ["mcp-plex-server"],
"env": {
"PLEX_SERVER_URL": "http://your-plex-server:32400",
"PLEX_TOKEN": "your_plex_token"
}
}
}
}
Or if running from a local clone:
{
"mcpServers": {
"plex": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-plex", "run", "mcp-plex-server"],
"env": {
"PLEX_SERVER_URL": "http://your-plex-server:32400",
"PLEX_TOKEN": "your_plex_token"
}
}
}
}
Tools
Discovery
| Tool | Parameters | Description |
|---|---|---|
search_media |
query, media_type="", limit=20 |
Search across all libraries. Optional type filter: "movie", "show", "episode", "artist", "album", "track". |
get_recently_added |
limit=20, library_name="" |
Recently added media, optionally filtered to a library. |
get_on_deck |
limit=10 |
Continue watching / next episode list. |
Library Browsing
| Tool | Parameters | Description |
|---|---|---|
get_libraries |
(none) | List all library sections with types and item counts. |
get_library_contents |
library_name, sort="titleSort", limit=50 |
Browse a library. Sort by title, date added, year, or rating. |
get_media_details |
rating_key |
Full details for one item: summary, genres, cast, directors, ratings. |
get_library_stats |
library_name="" |
Item counts and stats for one or all libraries. |
Shows
| Tool | Parameters | Description |
|---|---|---|
get_seasons |
rating_key |
List seasons for a TV show. |
get_episodes |
rating_key, season_number=0 |
List episodes (all or by season). |
Collections
| Tool | Parameters | Description |
|---|---|---|
get_collections |
library_name |
List collections in a library (includes smart/regular type). |
get_collection_items |
rating_key |
Get collection details and all items it contains. |
create_collection |
library_name, title, rating_keys |
Create a regular collection from specific items. |
create_smart_collection |
library_name, title, filters, libtype="", sort="", limit=0 |
Create a smart (filter-based) auto-updating collection. |
edit_collection |
rating_key, title="", summary=None, sort_order="", mode="" |
Edit collection metadata (title, summary, sort, display mode). |
add_to_collection |
rating_key, item_rating_keys |
Add items to a regular collection. |
remove_from_collection |
rating_key, item_rating_keys |
Remove items from a regular collection. |
delete_collection |
rating_key |
Delete a collection (does not affect the media items). |
Playlists
| Tool | Parameters | Description |
|---|---|---|
get_playlists |
(none) | List all playlists on the server. |
get_playlist_items |
rating_key |
Get items in a playlist. |
Watch State
| Tool | Parameters | Description |
|---|---|---|
mark_watched |
rating_key |
Mark a movie, episode, or track as fully watched. |
mark_unwatched |
rating_key |
Mark an item as unwatched, resetting progress. |
remove_from_continue_watching |
rating_key |
Remove a movie or episode from Continue Watching / On Deck. |
set_playback_progress |
rating_key, progress_ms |
Set playback position in milliseconds (must be > 0). |
Management
| Tool | Parameters | Description |
|---|---|---|
scan_library |
library_name |
Trigger a background library scan. |
Development
uv run mcp-plex-server # Run the server
uv run ruff check src/ # Lint
uv run ruff format src/ # Format
uv run pyright src/ # Type check
Pre-commit Hooks
This project uses lefthook for pre-commit checks. Install with brew install lefthook (or see other install methods), then:
lefthook install
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.