How do I get my Plex Token?

Log in to your Plex account at [**plex.tv**](https://plex.tv), go to **Settings > Server > General** and look for 'X-Plex-Token'. Alternatively, check your browser's network tab when loading the Plex web app.

What is my Server URL?

For local access: `http://YOUR_SERVER_IP:32400` (e.g. `http://192.168.1.100:32400`). For remote access: `https://YOUR_PLEX_SUBDOMAIN.plex.direct:32400`. The IP is your Plex server's local network address.

Can I see what's currently playing?

Yes! Use get_sessions to see all active playback sessions. Each session shows the user, media title, playback position, player device and whether it's direct playing or transcoding.

Can I search for specific media?

Yes! Use search_library with any title. Results include movies, TV shows, episodes, artists and albums matching your query. Optionally filter by library key to search in a specific library only.

Plex MCP Server for Pydantic AI 15 tools — connect in under 2 minutes

Name: Plex
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 15 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Plex through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Plex "
            "(15 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Plex?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Plex MCP Server

Connect to your Plex Media Server and manage your entire media library through natural conversation.

Pydantic AI validates every Plex tool response against typed schemas, catching data inconsistencies at build time. Connect 15 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Server Info — Check server status, version and connected clients
Active Sessions — See who's watching what right now with playback progress
Libraries — Browse all your media libraries (movies, shows, music, photos)
Search — Find any movie, episode, artist or album by name
Recently Added — Discover the newest additions to your library
On Deck — See what's next to continue watching
Metadata — Get full details on any media item including cast, file info and streams
Playlists — Browse and manage your playlists
Watch Status — Mark items as watched or unwatched

The Plex MCP Server exposes 15 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Plex to Pydantic AI via MCP

Follow these steps to integrate the Plex MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 15 tools from Plex with type-safe schemas

Why Use Pydantic AI with the Plex MCP Server

Pydantic AI provides unique advantages when paired with Plex through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Plex integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Plex connection logic from agent behavior for testable, maintainable code

Plex + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Plex MCP Server delivers measurable value.

Type-safe data pipelines: query Plex with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Plex tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Plex and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Plex responses and write comprehensive agent tests

Plex MCP Tools for Pydantic AI (15)

These 15 tools become available when you connect Plex to Pydantic AI via MCP:

get_all_episodes

Useful for getting the complete episode list for a series. Get all episodes of a TV show

get_children

For TV shows this returns seasons. For artists this returns albums. Requires the parent item's rating key. Get children of a media item (seasons or albums)

get_libraries

Each library includes its key (ID), type (movie, show, music, photo), title, agent, scanner and updated/created timestamps. Use the library key with other library tools. Get all libraries (sections) on the Plex server

get_library_content

Filter by type: type=1 for movies, type=2 for TV shows, type=8 for artists, type=13 for photos. Requires the library key from get_libraries. Get all content from a specific library

get_metadata

Returns title, summary, year, runtime, rating, genres, director, cast, media streams, file path and more. Get detailed metadata for a specific item

get_on_deck

Returns the next unwatched episode for each in-progress show. Get "On Deck" items (continue watching)

get_playlist_items

Returns the items with their titles, types, durations and metadata. Requires the playlist ID. Get items in a specific playlist

get_playlists

Each playlist includes its ID, title, type (video, audio, photo), item count and duration. Get all playlists on the Plex server

get_recently_added

Returns movies, episodes and albums with their titles, addition dates and metadata. Get recently added media to the library

get_server_info

Useful for verifying server connectivity and checking server health. Get Plex Media Server information

get_sessions

Each session includes the user, the media being watched (movie/episode), playback progress, player device, bandwidth and transcoding info. Get currently active streaming sessions

mark_unwatched

This resets the item's watch status. Requires the item's rating key. Mark a media item as unwatched

mark_watched

This affects the item's watch status and removes it from "On Deck". Requires the item's rating key. Mark a media item as watched

refresh_library

Useful after adding or removing files from your media folders. Requires the library key. Trigger a library scan/refresh

search_library

Returns matching movies, shows, episodes, artists and albums with their titles, types and metadata. Search the Plex media library

Example Prompts for Plex in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Plex immediately.

"Show me what's currently playing on my Plex server."

"Show me my movie libraries."

"What's on deck for me to watch?"

Troubleshooting Plex MCP Server with Pydantic AI

Common issues when connecting Plex to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Plex + Pydantic AI FAQ

Common questions about integrating Plex MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Plex MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.