Plex MCP Server
An MCP server for managing your Plex media library with AI assistants.
Plex MCP Server
A Model Context Protocol (MCP) server for Plex media management, enabling AI assistants like Claude to interact with your Plex library.
Features
- Movie Management: Search, browse, and analyze your movie collection
- Library Statistics: Get insights into your media collection
- Genre & Director Search: Find content by specific criteria
- Recent Additions: Track newly added content
- Extensible Architecture: Easy to add TV shows and other media types
Requirements
- Python 3.8 or higher
- Plex Media Server with accessible API
- Network access to your Plex server
Setup
Quick Setup (Recommended)
# Clone the repository
git clone https://github.com/richarddas/plex_mcp_server.git
cd plex_mcp_server
# Run the setup script (creates venv and installs dependencies)
./setup.sh
# Edit your Plex details
nano .env
# Activate virtual environment and start the server
source venv/bin/activate
python main.py
Manual Setup
-
Create and activate virtual environment:
python3 -m venv venv source venv/bin/activate -
Install dependencies:
pip install --upgrade pip pip install -r requirements.txt -
Configure environment variables:
cp .env.example .env nano .envUpdate the values in
.env:PLEX_URL: Your Plex server URL (e.g.,http://192.168.1.100:32400)PLEX_TOKEN: Your Plex authentication token (How to find it)HOSTandPORT: Server binding (defaults are fine for most setups)LOG_LEVEL: Logging verbosity (INFO recommended)
-
Run the server:
python main.py
Daily Usage
After initial setup, to run the server:
cd plex-mcp-server
source venv/bin/activate # Activate virtual environment
python main.py # Start server
# When done: deactivate # Exit virtual environment
Claude Desktop Configuration
Add to your Claude Desktop config.json:
{
"globalShortcut": "",
"mcpServers": {
"plex": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://your-server:8000/sse",
"--allow-http"
]
}
}
}
Available Tools
Movie Tools
get_library_stats- Overall library statisticslist_all_movies- Browse all movies with paginationsearch_movies- Search by titlesearch_by_genre- Find movies by genresearch_by_director- Find movies by directorsearch_by_year_range- Find movies by year rangeget_all_genres- List all available genresget_all_directors- List all directorsget_recent_movies- Recently added movies
Project Structure
plex_mcp_server/
├── main.py # FastAPI server
├── config.py # Configuration
├── plex_client.py # Plex connection
├── mcp_handler.py # MCP message handling
├── tools/
│ ├── movie_tools.py # Movie-related tools
│ └── tv_tools.py # TV tools (future)
└── requirements.txt # Dependencies
Development
To add new tools:
- Add methods to the appropriate tools file
- Update the
get_tool_definitions()method - Register the tool in
mcp_handler.py
License
MIT License
Похожие серверы
Meshh FX
Power your agents with deep Japan macro fx knowledge.
financekit-mcp
Financial market intelligence with 12 tools: real-time stock quotes, crypto prices, technical analysis (RSI, MACD, Bollinger Bands), market overview, and portfolio tracking. Zero API keys required.
Google Trends MCP
Connect Google Trends to Claude or ChatGPT via Two Minute Reports MCP. Analyze search demand, trending topics, and keyword interest to grow visibility.
ynab-mcp
MCP server for YNAB. Reconcile bank statements, itemize receipts, manage transactions — all through natural language.
MCP Cookie Server
Provides positive reinforcement to LLMs by awarding 'cookies' as treats.
Strider DoorDash
MCP server for DoorDash food delivery - AI agents can search restaurants, browse menus, and place delivery orders.
QR Business Cards
Create professional QR business cards via AI assistants. No API key required.
O'RLY Book Cover Generator
Generates O'RLY? (O'Reilly parody) book covers.
Fibrous MCP Server
A server for Fibrous Finance, a DeFi aggregation platform.
Hidden Empire
Play a legendary text adventure by talking to your AI — no commands to memorize. The Hidden Empire puts a full underground world of puzzles, treasures, and trolls inside your conversation. Speak naturally: say 'head north,' 'grab the lantern,' or 'what am I carrying?' and your AI handles the rest. Execute multi-move plans in one shot, undo mistakes instantly, and save up to 20 named playthroughs you can resume from any session. Based on the MIT-licensed Zork I source, rebuilt from the ground up for AI-native play.