How to Use the Kevel MCP in Pydantic AI

Q: Does Pydantic AI validate the output of Kevel list tools?

Yes, every JSON payload returned by tools like listcampaigns or listflights is validated against Pydantic models at runtime. This prevents malformed ad server data from breaking your application.

Build type-safe ad ops pipelines with Pydantic AI and the Kevel MCP Server to validate campaign data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to Pydantic AI

Create your Vinkius account to connect Kevel 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 Kevel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate campaign schemas at runtime

The Kevel MCP Server uses `get_campaign` and `list_campaigns` to integrate with Pydantic AI and guarantee that every ad entity matches your expected data models. When your agent calls these tools, the framework validates the JSON payload before your code processes it. This eliminates silent API failures. If Kevel returns an unexpected field format, Pydantic AI throws a validation error immediately instead of letting your agent hallucinate values.

Verify advertiser and creative relationships

This toolset uses `list_advertisers` and `list_creatives` to let your type-safe agent query advertiser details and creative assets. The agent calls these tools to verify that active assets are correctly mapped to their parent accounts. You write clean, typed Python code. By using `get_advertiser`, your agent fetches exact advertiser models and ensures all required fields are present before executing downstream logic.

Map inventory zones and flights with Pydantic AI

Your agent inspects your active inventory setup by querying `list_flights`, `list_sites`, and `list_zones`. The framework serializes these lists into typed Python objects, making it easy to run programmatic checks. You get complete structural confidence. The agent uses `list_ad_types` and `list_channels` to verify that your active flights match the physical layout of your digital properties.

Setup guide

Set up Kevel 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": {
        "kevel-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You initialize MCPToolset with your Vinkius HTTP URL and pass it to the agent constructor. This registers all eleven tools, giving your Pydantic AI agent direct, type-safe access to your ad server.

Yes, every JSON payload returned by tools like `list_campaigns` or `list_flights` is validated against Pydantic models at runtime. This prevents malformed ad server data from breaking your application.

Yes, Vinkius handles the hosting and exposes a secure, single-endpoint token. Your Pydantic AI agent connects to this managed MCP Server, removing the need to manage complex network tunnels.

No, MCPServerHTTP is deprecated. You should use the unified MCPToolset class to connect your agent to the external Kevel server.

The server runs in an isolated V8 sandbox on Vinkius, which handles authentication on your behalf. Your Kevel API tokens are injected securely at the edge, so your agent never exposes them in raw network logs.

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