How to Use the api.video MCP in Pydantic AI

Q: How do I install the api.video integration for Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Then instantiate an MCPToolset with your Vinkius MCP Server endpoint URL. Pass that toolset array to your Agent object.

Q: Is MCPServerHTTP still supported for api.video in Pydantic AI?

No. That class is deprecated. You must use the unified MCPToolset approach with a standard HTTP string to connect to the external Vinkius MCP Server.

Bring strict type validation to your api.video workflows by connecting Pydantic AI to our managed MCP Server endpoint.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect api.video MCP to Pydantic AI

Create your Vinkius account to connect api.video to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup api.video with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Validation for Pydantic AI

The `create_video_object` tool requires exact string formats for titles and descriptions. Pydantic AI forces your agent to build the request payload against a strict schema before sending it to the MCP Server endpoint. If the model hallucinates a required field, the framework throws a validation error immediately. This strictness applies to `update_video_details` too. You define the acceptable metadata structures in Python. The agent can't push malformed JSON to your video hosting platform because the runtime catches it first.

Type-Safe Metric Retrieval

`get_video_analytics` and `get_video_details` return deeply nested JSON containing viewer metrics and encoding statuses. When your agent queries these endpoints, Pydantic parses the response into typed Python objects. There's no silent data corruption. If the API returns an unexpected date format from `list_videos`, your script halts. You fix the model definition instead of downstream systems crashing. You use the `MCPToolset` class pointing to the HTTP endpoint to handle this data flow.

Model-Agnostic Media Management

`list_video_captions` and `list_video_chapters` pull structural metadata that your agent uses to generate summaries. `list_player_themes` fetches UI configurations. Your agent can run on local models, Anthropic, or OpenAI. The framework stays completely agnostic. You just install the slim package with the MCP extra, and the agent knows exactly how to read the Vinkius server tools. `delete_video` remains available, but its inputs face heavy scrutiny by your schema definitions before execution.

Setup guide

Set up api.video 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": {
        "apivideo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent api.video 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 api.video. 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 api.video 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 api.video MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Then instantiate an `MCPToolset` with your Vinkius MCP Server endpoint URL. Pass that toolset array to your Agent object.

Runtime validation prevents bad data from reaching the API. If your agent tries to send an invalid parameter to `update_video_details`, Pydantic catches the error locally.

No. That class is deprecated. You must use the unified `MCPToolset` approach with a standard HTTP string to connect to the external Vinkius MCP Server.

Yes. The framework is completely model-agnostic. As long as your local LLM can follow the tool schema for `get_video_analytics`, it can pull and analyze your viewer metrics.

The server processes chapter timestamps, tag arrays, and caption files. Vinkius enforces a zero-trust model where authentication tokens are never stored at rest. Every request requires a fresh validation check.

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