How to Use the Ask Kodiak MCP in OpenAI Agents SDK

Q: How do I connect the Ask Kodiak MCP to the OpenAI Agents SDK?

Initialize MCPServerStreamableHttp with your Vinkius URL. Pass it to the mcpservers array in your Agent constructor. The SDK auto-discovers the tools immediately.

Q: Can my OpenAI Agents SDK system search specific Ask Kodiak carriers?

Yes. Your agent runs listcompanies to pull the carrier list. It then uses getcompanyproducts to filter exact commercial offerings for that specific market.

Q: Does the agent cache insurance products?

You control the cache. Setting cacheToolsList=True caches the tool definitions, but the actual data pulled from listproducts remains live to ensure accurate appetite matching.

Connect the Ask Kodiak MCP Server to your OpenAI Agents SDK pipeline to automate commercial insurance appetite matching.

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 OpenAI Agents SDK

Create your Vinkius account to connect Ask Kodiak to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build production insurance agents with this MCP Server

Your OpenAI agent needs to know which carrier writes what risk. Passing the `list_products` tool directly into your agent constructor lets it query commercial insurance markets instantly. You get real-time appetite data without writing custom API wrappers. Handoffs make this powerful. You configure a specialized routing agent to run `suggest_naics` based on a user's business description. Once the classification is locked, it hands off to a quoting agent that fires `get_company_products` to pull specific carrier details.

Validate carrier appetite automatically

Guardrails keep your agents from hallucinating coverage options. When your system calls `get_product`, OpenAI validates the action before execution. It checks the exact appetite parameters against your defined safety constraints. You never show a client an unsupported policy. The agent uses `list_companies` to verify carrier status, and the OpenAI dashboard traces every single API call back to the original prompt.

Map industry codes instantly

Finding the right NAICS code usually requires manual database searches. Your agent handles this autonomously using `list_classifications`. It reads the business context and pulls the exact industry codes required for underwriting. Setup takes seconds. You initialize `MCPServerStreamableHttp` with your Vinkius endpoint, set `cacheToolsList=True` to speed up discovery, and your agent is ready to quote. Confirm the connection anytime with `get_account_check`.

Setup guide

Set up Ask Kodiak MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Ask Kodiak tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Ask Kodiak tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Ask Kodiak tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Ask Kodiak Agent",
            instructions="You have access to Ask Kodiak tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Initialize `MCPServerStreamableHttp` with your Vinkius URL. Pass it to the `mcp_servers` array in your Agent constructor. The SDK auto-discovers the tools immediately.

Yes. Your agent runs `list_companies` to pull the carrier list. It then uses `get_company_products` to filter exact commercial offerings for that specific market.

You skip writing integration code. The agent gets native access to `suggest_naics` and `get_product` while you benefit from OpenAI's built-in tracing and action validation.

You control the cache. Setting `cacheToolsList=True` caches the tool definitions, but the actual data pulled from `list_products` remains live to ensure accurate appetite matching.

Your Vinkius endpoint runs in an isolated V8 sandbox. When your agent queries NAICS codes or carrier appetite data, the transaction is ephemeral. Zero data persists after the HTTP 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