How to Use the Ask Kodiak MCP in LangChain

Q: How does my LangChain agent find which products a carrier offers with Ask Kodiak?

Your agent calls the getcompanyproducts tool with the carrier's name. It gets back a list of all products that company provides. You can chain this with listcompanies to first find the carrier if you don't know the exact name.

Q: Can a LangChain agent check if a product covers a 'landscaping' business using Ask Kodiak?

Yes. The agent would first use suggestnaics with 'landscaping' to get the right industry code. Then it calls getproduct with that code and the product ID to check the product's appetite details.

Q: What's the best way to search for NAICS codes with Ask Kodiak in LangChain?

Use the suggestnaics tool. Give your agent a plain-text description of the business, and the tool returns a list of potential NAICS codes. It's much faster than looking them up in a directory.

Q: How do I confirm my connection to the MCP Server is working?

Just have your agent call the getaccountcheck tool. It's a simple ping that returns a success message if your endpoint and token are valid.

Build agents in LangChain that find the right insurance carrier by chaining Ask Kodiak tool calls together.

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 LangChain

Create your Vinkius account to connect Ask Kodiak to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Carrier and Product Lookups

Give your agent a goal, not a script. It can use `list_companies` to find carriers, then immediately feed that output into `get_company_products` to see what each one offers. This avoids all the manual copy-pasting between steps. Build more complex reasoning chains. For instance, an agent can find a product with `list_products`, get its full appetite details with `get_product`, and then find related industry codes using `suggest_naics`. LangSmith lets you watch the whole process and see exactly what the agent decided to do.

Find Industry Codes Programmatically

Stop guessing NAICS codes. Give your LangChain agent a business description and have it call `suggest_naics`. It gets back a list of relevant codes, not just one guess. Then, the agent can take those codes and automatically search for matching insurance products using the `list_products` tool. It's a simple, two-step chain that connects a business type to available coverage in seconds.

Your LangChain Insurance Research Agent

This MCP Server gives your agent seven specific tools for commercial insurance. You can build a ReAct agent that decides which tool to use based on your prompt, like checking carrier appetite with `get_product` or finding a specific company with `list_companies`. The agent isn't just following a rigid workflow. It can handle dead ends. If `list_products` returns nothing, it can try a broader search with `list_classifications` to find a different angle. That's the point of giving an agent tools instead of just an API.

Setup guide

Set up Ask Kodiak MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Ask Kodiak tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ask-kodiak-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Ask Kodiak transactions"
    })
    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 LangChain

Your agent calls the `get_company_products` tool with the carrier's name. It gets back a list of all products that company provides. You can chain this with `list_companies` to first find the carrier if you don't know the exact name.

Yes. The agent would first use `suggest_naics` with 'landscaping' to get the right industry code. Then it calls `get_product` with that code and the product ID to check the product's appetite details.

Use the `suggest_naics` tool. Give your agent a plain-text description of the business, and the tool returns a list of potential NAICS codes. It's much faster than looking them up in a directory.

Just have your agent call the `get_account_check` tool. It's a simple ping that returns a success message if your endpoint and token are valid.

Your queries about insurance carriers, products, and NAICS codes are sent to the Ask Kodiak server but are not stored by Vinkius. Each request runs in an ephemeral, sandboxed environment, and the connection is secured end-to-end.

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