Compatible with every major AI agent and IDE
What is the Vidyard MCP Server?
Connect your Vidyard account to any AI agent and manage your business video library through natural conversation.
What you can do
- Video Library — List all video assets stored in your Vidyard dashboard and retrieve unique video IDs
- Metadata & Details — Get technical metadata for any video including length, encoding status, and descriptions
- Player Management — Create, update, and manage video players (facades) to customize how your content is embedded
- Video Organization — Attach videos to specific players and organize your content for different marketing or sales needs
- Direct Stream Access — Retrieve direct stream URLs and raw MP4 download links for various video qualities (480p, 720p, etc.)
- Asset Management — Rename players or permanently delete video assets and player containers from your dashboard
How it works
- Subscribe to this server
- Enter your Vidyard API Token
- Start managing your video library through Claude, Cursor, or any MCP-compatible client
No more manual browsing through complex video dashboards. Your AI agent becomes your video asset manager.
Who is this for?
- Marketing Teams — organize video players for different campaigns and retrieve embed codes through chat
- Sales Professionals — quickly find and share specific videos or product demos with prospects
- Content Creators — manage video assets, check encoding status, and retrieve source files for distribution
- Support Engineers — find relevant tutorial videos and manage player branding for knowledge base articles
Built-in capabilities (10)
Requires both player ID and video ID. Adds a video asset into a specific player container
Creates a new, empty video player container
This action is irreversible. Permanently deletes a video asset from Vidyard
Note that the original video assets are not deleted. Permanently deletes a video player
Retrieves details for a specific video player
Retrieves technical metadata for a specific video asset
Retrieves direct stream URLs for various video qualities (480p, 720p, etc.)
Lists all configured video players (facades) in the account
Lists all video assets stored in the Vidyard dashboard
Updates the display name or title of an existing player
Why Pydantic AI?
Pydantic AI validates every Vidyard tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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 Vidyard integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Vidyard connection logic from agent behavior for testable, maintainable code
Vidyard in Pydantic AI
Vidyard and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Vidyard 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 | 4,000+ 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 Vidyard in Pydantic AI
The Vidyard 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 10 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
Vidyard for Pydantic AI
Every tool call from Pydantic AI to the Vidyard MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I get direct download links for my videos through the agent?
Yes. The get_video_source_files tool allows your agent to retrieve direct MP4 download links and stream URLs for different qualities (like 720p or 1080p), making it easy to share raw files or use them in other applications.
How do I add a video to a specific player?
Use the attach_video_to_player tool. You'll need to provide the player_id and the video_id. Your agent can help you find these IDs by listing your players and videos first.
Can I create new video players through conversation?
Absolutely. The create_empty_player tool lets you provision a new player container with a descriptive name. Once created, you can attach videos to it and manage its settings directly through your agent.
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 Vidyard MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai
Explore More MCP Servers
View all →
Nango (Unified API & Integration Platform)
7 toolsManage product integrations via Nango — audit OAuth connections, track data syncs, and explore unified records.

Caiyun AI Translate / 彩云小译
10 toolsPopular high-precision machine translation — translate text lists and detect languages via AI.

EZO Asset Intelligence
10 toolsEquip your AI agent to manage fixed assets, track inventory, and monitor checkouts via the EZO.io (EZOfficeInventory) API.

Covalent
10 toolsEquip your AI agent to query unified blockchain data including balances, transactions, and NFTs across 100+ chains.
