How to Use the Ask Kodiak MCP in Pydantic AI

Q: How do I add the Ask Kodiak MCP to a Pydantic AI agent?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius URL and add it to your Agent's toolsets list.

Q: Why use the unified MCPToolset approach?

The older MCPServerHTTP class is deprecated. MCPToolset provides a cleaner, safer way to bind external tools to your agent while maintaining strict type boundaries.

Type-safe commercial insurance searches for your Pydantic AI agents using the Ask Kodiak MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ask Kodiak MCP to Pydantic AI

Create your Vinkius account to connect Ask Kodiak 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 Ask Kodiak with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ask Kodiak MCP Server for strict type safety

Insurance data requires absolute precision. When your Pydantic AI agent queries this MCP Server, every response is validated against strict Pydantic models at runtime. If a carrier API changes a field, your agent fails loudly instead of hallucinating coverage. You build agents that prioritize correctness. By giving your agent access to `get_product`, it pulls exact appetite parameters. The framework ensures the returned data structures match your expectations exactly before the LLM even sees them.

Model-agnostic carrier matching

You are not locked into one LLM provider. Whether you run Anthropic, OpenAI, or a local model, the agent interacts with `list_products` exactly the same way. The framework normalizes the tool calls. Industry classification becomes predictable. Your agent fires `suggest_naics` to categorize a business risk. Because Pydantic enforces the schema, the resulting NAICS codes are always formatted correctly for your downstream underwriting systems.

Unified toolset integration

Connecting external systems used to mean writing endless validation logic. Now you just initialize `MCPToolset` with your Vinkius HTTP endpoint. Pass it to the `toolsets` array in your Agent constructor, and the tools are live. Your agent manages the market search autonomously. It runs `list_companies` to find available carriers, then calls `get_company_products` for specific lines of business. You check the connection status anytime with `get_account_check`.

Setup guide

Set up Ask Kodiak 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": {
        "ask-kodiak-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius URL and add it to your Agent's `toolsets` list.

Yes. The framework enforces strict runtime validation on every response from `get_product` or `list_classifications`. If the data shape is wrong, it throws a validation error.

You can. The framework is completely model-agnostic. Your local LLM can call `suggest_naics` just as easily as GPT-4 does.

The older `MCPServerHTTP` class is deprecated. `MCPToolset` provides a cleaner, safer way to bind external tools to your agent while maintaining strict type boundaries.

Your connection uses a single secure endpoint token. When your agent pulls commercial insurance products or carrier appetite details, the traffic routes through a stateless V8 isolate that destroys itself after the request.

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