Bring Digital Signage
to Pydantic AI
Learn how to connect FusionSignage to Pydantic AI and start using 17 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the FusionSignage MCP Server?
Connect your FusionSignage account to any AI agent and manage your digital signage network through natural conversation.
What you can do
- Screen Management — List all screens with online/offline status, inspect configurations, update settings, and check real-time connectivity
- Playlist Builder — Create, update, and delete content playlists with media items and display order
- Content Assignment — Assign playlists to specific screens for targeted content delivery
- Media Library — Browse all uploaded media (images, videos, web pages), inspect file metadata, and remove outdated assets
- Content Scheduling — Create time-based schedules with playlist rotation and screen assignments
- Screen Groups — Organize screens into groups for bulk content management
How it works
1. Subscribe to this server
2. Enter your FusionSignage API Key from your account settings
3. Start managing your signage network from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Facility Managers — monitor screen status, push content updates, and manage display groups without accessing the dashboard
- Marketing Teams — schedule campaigns, rotate promotional content, and update digital menus through AI
- IT Administrators — audit screen connectivity, manage media libraries, and troubleshoot display issues
Built-in capabilities (17)
Assign playlist to screen
Verify connectivity
Create a playlist
Create a schedule
Delete media
Delete a playlist
Get media details
Get playlist details
Get screen details
Get screen status
List screen groups
List all media
List all playlists
List schedules
List all screens
Update a playlist
Update a screen
Why Pydantic AI?
Pydantic AI validates every FusionSignage tool response against typed schemas, catching data inconsistencies at build time. Connect 17 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.
- —
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 FusionSignage integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your FusionSignage connection logic from agent behavior for testable, maintainable code
FusionSignage in Pydantic AI
FusionSignage and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect FusionSignage to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for FusionSignage in Pydantic AI
The FusionSignage 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. All 17 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
FusionSignage for Pydantic AI
Every tool call from Pydantic AI to the FusionSignage MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I monitor which screens are online or offline in real time?
Yes. Use list_screens to see all screens with their current online/offline status and assigned content. For a specific screen, use get_screen_status to check real-time connectivity and playback status. Use get_screen for detailed configuration including orientation and playlist assignment.
Can I create a playlist and assign it to a screen?
Yes. Use create_playlist with a JSON payload containing name and media items. Then use assign_playlist with the screen ID and playlist ID to push it to a display. Use update_playlist to modify content order or add new media, and delete_playlist to remove unused playlists.
Can I schedule content to play at specific times?
Yes. The create_schedule tool accepts a JSON configuration with time slots, playlist rotations, and screen assignments. Use list_schedules to view all active schedules. Combine with list_groups to manage multiple screens simultaneously through group assignments.
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 FusionSignage MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai