mcp-tautulli
A single file simple MCP server tracking 11 relevant tautulli metrics.
README
mcp-tautulli
A single-file MCP server for Tautulli — Plex monitoring via Claude Code (or any MCP client).
11 read-only tools. No mutations. All configuration via environment variables.
Prerequisites
- Python 3.10+
- A running Tautulli instance with an API key
- Claude Code (or any MCP-compatible client)
Installation
pip install mcp-tautulli
Or from source:
git clone https://github.com/lodordev/mcp-tautulli.git
cd mcp-tautulli
pip install .
Configuration
Three environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
TAUTULLI_URL |
Yes | — | Tautulli base URL (e.g. http://localhost:8181) |
TAUTULLI_API_KEY |
Yes | — | Tautulli API key (Settings → Web Interface → API Key) |
TAUTULLI_TLS_VERIFY |
No | true |
Set to false if using self-signed certs (e.g. Tailscale serve) |
Claude Code Setup
Add to your project's .mcp.json:
{
"mcpServers": {
"tautulli": {
"command": "python",
"args": ["/path/to/tautulli.py"],
"env": {
"TAUTULLI_URL": "http://your-tautulli-host:8181",
"TAUTULLI_API_KEY": "your-api-key-here"
}
}
}
}
Or run standalone:
export TAUTULLI_URL="http://localhost:8181"
export TAUTULLI_API_KEY="your-api-key"
python tautulli.py
Tools
| Tool | Description |
|---|---|
tautulli_activity |
Current Plex streaming activity — who's watching what, progress, quality |
tautulli_history |
Recent playback history with filters (user, media type, search, date) |
tautulli_user_stats |
Per-user watch statistics — plays, watch time, last seen |
tautulli_library_stats |
Library item counts, total plays, last played per library |
tautulli_most_watched |
Top content by plays or duration (TV, movies, music, users) |
tautulli_server_info |
Plex server identity — name, version, platform, connection |
tautulli_status |
Server config and reachability check |
tautulli_transcode_stats |
Direct play vs transcode breakdown by platform |
tautulli_platform_stats |
Top platforms/devices by plays and watch time |
tautulli_stream_resolution |
Source vs delivered resolution analysis |
tautulli_plays_by_date |
Daily play counts over time by stream type |
All tools are read-only — this server does not modify any Tautulli or Plex state.
License
MIT
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.