How to Use the GAN.ai MCP in Pydantic AI

Q: How do I inject GAN.ai into a Pydantic AI agent?

Install pydantic-ai-slimmcp. Create an MCPToolset with your HTTP endpoint and pass it to the agent toolsets array. The old MCPServerHTTP class is deprecated.

Q: How does Pydantic AI validate GAN.ai API responses?

Every return value from tools like getvideostats is checked against a Pydantic schema at runtime. If the payload deviates, the framework throws a validation error immediately.

Q: Can Pydantic AI track GAN.ai rendering progress?

Your agent polls getgenerationstatus. Because the framework is model-agnostic, you can use a fast local model to handle this repetitive polling task cheaply.

Q: How do I list video projects with this integration?

The agent executes listvideoprojects. It retrieves the IDs and enforces strict type checks on the returned metadata.

Type-safe GAN.ai video generation using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GAN.ai MCP to Pydantic AI

Create your Vinkius account to connect GAN.ai 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 GAN.ai with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strongly Typed Video Generation

Your agent calls `generate_personalized_videos` and Pydantic AI validates the payload before it even hits the network. It checks `get_project_metadata` to ensure your variables match the template schema perfectly. If a field is missing, the agent fails loudly. You avoid silent corruption entirely. When you need a one-off asset, the agent triggers `generate_single_video`. The strict typing guarantees the API receives exactly what it expects, preventing wasted rendering costs from malformed requests.

Validated Analytics via MCP Server

Once a campaign is live, your agent pulls engagement data using `get_video_stats`. Pydantic AI parses the JSON response into a strict model. If the API returns an unexpected structure, the system catches it instantly. The agent also checks `list_generated_videos` to audit historical output. It reads `get_video_metadata` to confirm URLs and thumbnail links are properly formatted. Your analytics pipeline stays perfectly clean.

Audit Webhooks and Workspaces

Agents use `verify_api_connection` to establish a baseline before executing complex logic. They call `get_workspace_info` to map out available resources. Every response is cast into a predictable object. To ensure callbacks hit your servers, the agent inspects `list_configured_webhooks`. It pairs this with `list_landing_templates` to verify the end-to-end user journey. You build autonomous marketing systems that actually respect your data contracts.

Setup guide

Set up GAN.ai 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": {
        "ganai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent GAN.ai 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 GAN.ai. 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 GAN.ai 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 GAN.ai MCP in Pydantic AI

Install pydantic-ai-slim[mcp]. Create an MCPToolset with your HTTP endpoint and pass it to the agent toolsets array. The old MCPServerHTTP class is deprecated.

Every return value from tools like `get_video_stats` is checked against a Pydantic schema at runtime. If the payload deviates, the framework throws a validation error immediately.

Your agent polls `get_generation_status`. Because the framework is model-agnostic, you can use a fast local model to handle this repetitive polling task cheaply.

The agent executes `list_video_projects`. It retrieves the IDs and enforces strict type checks on the returned metadata.

The server processes names, company details, and personalized text strings. All traffic routes through an isolated execution environment. No data writes to disk, and the execution layer is destroyed the millisecond the API connection closes.

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