How to Use the Shotstack MCP in Pydantic AI

Q: How does Pydantic AI handle render job IDs with Shotstack?

When you get a render ID from rendervideo, it's validated against a type-safe model. This means your agent knows exactly what format the ID is in, preventing runtime errors when passing it to other tools.

Q: What if I need to audit assets after running Shotstack with Pydantic AI?

Use listassetsfromrender and pass the job ID. The returned data is validated, confirming that every associated asset detail matches the expected structure for your agent's review.

Q: How do I check my history of renders with Shotstack and Pydantic AI?

Running listrecentrenders returns structured data that your agent can immediately use. The results are validated, giving you confidence in the render history.

Ensure data correctness when building videos with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shotstack MCP to Pydantic AI

Create your Vinkius account to connect Shotstack to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Shotstack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Video Rendering via MCP Server

When you need to start a video, call `render_video` and get the resulting render ID. This job generates personalized content from templates, and Pydantic AI validates that all necessary parameters were passed correctly before execution. You can check on progress using `get_render_status`. The response is typed, meaning if the API gives bad status data, your agent fails loudly—no silent corruption.

Asset Management for Pydantic AI

To bring in source media, use `ingest_media_source` to upload assets. The output schema confirms the asset's existence and details. This prevents your agent from using a file that technically doesn't exist. Check what files are available for rendering by calling `list_hosted_assets`. You get structured data back, so you know exactly what media is ready.

Template Management with MCP Server

Before generating anything, define the structure using `create_video_template` to save an edit. Because Pydantic AI validates schemas, any template change results in a clear error, catching bad logic before it hits production. Use `list_templates` to see all available structures. The data returned confirms that every listed template adheres to the expected schema.

Setup guide

Set up Shotstack MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "shotstack-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Shotstack tools.",
)

result = await agent.run("List recent Shotstack transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Shotstack. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Shotstack now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Shotstack MCP in Pydantic AI

When you get a render ID from `render_video`, it's validated against a type-safe model. This means your agent knows exactly what format the ID is in, preventing runtime errors when passing it to other tools.

Use `list_assets_from_render` and pass the job ID. The returned data is validated, confirming that every associated asset detail matches the expected structure for your agent's review.

Yes. Your workflows are safe because any step—from template listing (`list_templates`) to rendering—must conform to a defined schema. This correctness is key when scaling personalized videos.

Running `list_recent_renders` returns structured data that your agent can immediately use. The results are validated, giving you confidence in the render history.

The server touches hosted asset details and render job IDs. Your agent is handling uploaded source assets—temporary input media sources—and these are treated with strict schema validation throughout the process.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript