How to Use the HealthCare.gov MCP in LlamaIndex

Q: How do I use LlamaIndex to find all HealthCare.gov plans that cover a specific drug?

This is a multi-step RAG process. Your agent would first searchplans for a given area, then loop through the resulting plan IDs, calling getdrugcoverage for each one. You can then index the plans that return a positive match, creating a knowledge base of plans that cover that medication.

Use LlamaIndex to index live HealthCare.gov data, creating a RAG agent that answers questions based on actual plan details.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HealthCare.gov MCP to LlamaIndex

Create your Vinkius account to connect HealthCare.gov 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 HealthCare.gov with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Marketplace Data

Turn API calls into a durable, searchable knowledge base. Your LlamaIndex agent can use the `search_plans` tool to fetch all plans for a given area, then you can index the results directly into a vector store. Now, your agent doesn't need to call the API for every question. It can perform a vector search over the indexed plan data, giving you fast, consistent answers to questions like "show me all the silver plans I looked at yesterday."

Ground Answers in Specific Plan Details

Build a RAG pipeline that pulls in facts, not just search results. When a user asks about a specific plan, your agent can call `get_plan_details`, `get_drug_coverage`, and `get_provider_coverage` in real time. The outputs are then fed into the LLM as context. This forces the agent's response to be grounded in the actual data from the HealthCare.gov API. The result is a summary that accurately reflects a plan's deductible, drug tiers, and network status, because the data was retrieved moments before the answer was generated.

Build a Custom HealthCare.gov Query Engine

Combine multiple tools to answer complex questions. The `McpToolSpec` lets your agent see all 11 tools. It can learn to combine them, for instance, using `get_counties_by_zip` before `search_plans` to properly scope a search. By indexing the outputs of these tool combinations, your LlamaIndex application becomes a specialized query engine for the health insurance marketplace. You're not just calling an MCP tool; you're building a private, queryable model of the market data.

Setup guide

Set up HealthCare.gov 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 HealthCare.gov 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 HealthCare.gov tools.",
)
response = await agent.run("List recent HealthCare.gov 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 HealthCare.gov. 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 HealthCare.gov 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 HealthCare.gov MCP in LlamaIndex

This is a multi-step RAG process. Your agent would first `search_plans` for a given area, then loop through the resulting plan IDs, calling `get_drug_coverage` for each one. You can then index the plans that return a positive match, creating a knowledge base of plans that cover that medication.

Yes. You'd provide the agent with a list of doctors. It would use `search_providers` to get their IDs, then query against plans using `get_provider_coverage`. The agent can synthesize the results to find plans where all listed doctors are in-network.

LlamaIndex lets you index the results. Instead of making repetitive API calls, you build a local, searchable knowledge base from the HealthCare.gov data. This allows your agent to answer questions about data it has already seen, making it faster and more consistent.

The data is generally updated once for each Open Enrollment period. While plan details are stable during that time, information like provider networks can change. Your agent should treat the data as a snapshot and note that in its responses.

You control where the data goes. This MCP server securely fetches plan, drug, and provider information from HealthCare.gov for your agent. When you index that data, it's stored in the vector database *you* configure. The security of the indexed data is your responsibility; the security of the data in transit is handled by Vinkius.

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