How to Use the Ask Kodiak MCP in AutoGen

Q: Can an AutoGen agent group use Ask Kodiak to determine if a carrier is a good fit for a new client?

Yes. One agent can pull the client's industry with suggestnaics. A second agent can then take that code and use getcompanyproducts to see if a preferred carrier offers anything suitable. They'll debate the results in the chat.

Q: How do my AutoGen agents get access to the Ask Kodiak tools for a debate?

You use the mcpservertools function from the autogen-ext package, pointing it at your server URL. This provides the tools list that you pass to your AssistantAgent constructors. The agents can then call tools like listcompanies during their conversation.

Q: Is there a simple tool to test the connection from my AutoGen setup?

Yes, have any agent call the getaccountcheck tool. It takes no arguments and will confirm if the MCP Server is reachable and your authentication is working.

Let AutoGen agents debate and find the best commercial insurance coverage from Ask Kodiak's data.

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 AutoGen

Create your Vinkius account to connect Ask Kodiak to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Carrier Options

Set up two agents with different goals. One agent's job is to find the broadest coverage by calling `list_products` and `get_product`. A second, more conservative agent, can use `list_companies` to prioritize carriers you already have a relationship with. They'll discuss the findings in a group chat. The first agent might propose a new product, while the second agent challenges it, forcing a consensus on the best option based on the goals you gave them.

Converge on the Right Classification

Finding the right NAICS code for a niche business is hard. One AutoGen agent can use `suggest_naics` with a broad query, while another uses `list_classifications` with a more specific one. The agents then present their findings to each other. They can debate which classification is a better fit, asking for more details until they agree on the code that best represents the business risk before they even start searching for products.

Multi-Agent Research with an MCP Server

This MCP server equips your agents with the tools to interact with the Ask Kodiak database. You can create a `ResearcherAgent` that uses `list_products` and a `VerifierAgent` that double-checks details with `get_product`. AutoGen orchestrates the conversation between them. The researcher proposes a product, the verifier confirms it covers the client's industry, and a `UserProxyAgent` presents you with the final, validated recommendation.

Setup guide

Set up Ask Kodiak MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Ask Kodiak tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Ask Kodiak_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Ask Kodiak data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Ask Kodiak_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Ask Kodiak data")
    print(result.messages[-1].content)

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 AutoGen

Give both agents access to the Ask Kodiak tools. Instruct one to use `list_products` to generate a list of options. Then, have the second agent review that list and use `get_product` to find the best fit based on a different criteria, like appetite for a specific state.

Yes. One agent can pull the client's industry with `suggest_naics`. A second agent can then take that code and use `get_company_products` to see if a preferred carrier offers anything suitable. They'll debate the results in the chat.

You use the `mcp_server_tools` function from the `autogen-ext` package, pointing it at your server URL. This provides the tools list that you pass to your `AssistantAgent` constructors. The agents can then call tools like `list_companies` during their conversation.

Yes, have any agent call the `get_account_check` tool. It takes no arguments and will confirm if the MCP Server is reachable and your authentication is working.

Only the specific queries you send, like product names or business descriptions for NAICS lookups. This data travels over a TLS-encrypted connection to an isolated Vinkius sandbox that is destroyed after your request is complete. No query history is retained on our platform.

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