How to Use the Ask Kodiak MCP in LlamaIndex

Q: How can a LlamaIndex app use Ask Kodiak to find all insurance carriers?

You use the McpToolSpec to expose the listcompanies tool to your agent. When called, it returns a list of carriers that LlamaIndex can then index into your vector store for future queries.

Q: Can I build a RAG pipeline with LlamaIndex that uses Ask Kodiak to compare products?

Yes. Have your agent call listproducts with your search terms, then loop through the results and call getproduct for each one. LlamaIndex will index all the detailed product appetites, making them easy to compare through a simple query.

Q: What's the difference between listproducts and getproduct with Ask Kodiak in LlamaIndex?

listproducts is for discovery—it returns a list of products matching your search. getproduct is for details—it takes a specific product ID and gives you the full appetite info. A common pattern is to find products with the first tool, then index the details with the second.

Q: How do I check my connection from LlamaIndex to the Ask Kodiak server?

The getaccountcheck tool is for this. Call it from your agent; a successful response means your endpoint and token are correct.

Turn Ask Kodiak's insurance data into a queryable knowledge base for your LlamaIndex RAG apps.

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 LlamaIndex

Create your Vinkius account to connect Ask Kodiak to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Carrier Appetite in Real-Time

Use the `get_product` and `get_company_products` tools to pull fresh carrier appetite data from Ask Kodiak. LlamaIndex doesn't just show you the data once; it indexes the results into your chosen vector store. Now your RAG application can answer questions like 'Which carriers we looked at yesterday cover plumbers?' without re-running API calls. The answers are grounded in the real data you just indexed from this MCP Server.

Build a Semantic Search for NAICS

Run a few queries with `suggest_naics` and `list_classifications`. LlamaIndex will automatically capture and index these industry classifications and their descriptions. This creates a specialized knowledge base for your agent. You can then ask complex questions in natural language, and your LlamaIndex app will find the most relevant NAICS codes from the data it has already processed.

Ground Your LlamaIndex Agent in Facts

An agent is only as good as its data. This MCP Server provides the raw data about insurance products and carriers through tools like `list_products` and `list_companies`. By indexing the output of these tool calls, you build a trusted, local data source for your agent. It stops hallucinating and starts giving answers based on the actual carrier information you fetched from Ask Kodiak.

Setup guide

Set up Ask Kodiak MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Ask Kodiak MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Ask Kodiak tools.",
)
response = await agent.run("List recent Ask Kodiak data")

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 LlamaIndex

You use the `McpToolSpec` to expose the `list_companies` tool to your agent. When called, it returns a list of carriers that LlamaIndex can then index into your vector store for future queries.

Yes. Have your agent call `list_products` with your search terms, then loop through the results and call `get_product` for each one. LlamaIndex will index all the detailed product appetites, making them easy to compare through a simple query.

`list_products` is for discovery—it returns a list of products matching your search. `get_product` is for details—it takes a specific product ID and gives you the full appetite info. A common pattern is to find products with the first tool, then index the details with the second.

The `get_account_check` tool is for this. Call it from your agent; a successful response means your endpoint and token are correct.

No. Vinkius processes your requests for carrier and product data in a zero-trust environment. The data from Ask Kodiak passes through our ephemeral sandbox, but nothing about your queries is logged or saved on our 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