How to Use the HealthCare.gov MCP in LangChain

Q: How can my LangChain agent compare two HealthCare.gov plans side-by-side?

Your agent should call getplandetails for each of the two plan IDs. It can then parse the resulting JSON objects to extract and compare key fields like deductibles, out-of-pocket maximums, and monthly premiums.

Q: What's the best way to find plans in a specific ZIP code using HealthCare.gov and LangChain?

The right way is a two-step chain. First, the agent calls getcountiesbyzip with the ZIP code to get the county FIPS code. Then, it uses that FIPS code in the searchplans tool to get accurate results for that specific market.

Q: Can I build a LangChain agent to check if my doctor is covered by a HealthCare.gov plan?

Yes. The agent would use searchproviders to find the exact ID for your doctor. Then it would pass that provider ID and a plan ID to the getprovidercoverage tool to get a definitive yes or no on in-network coverage.

Build LangChain agents that chain HealthCare.gov plan, drug, and provider searches to find the objectively best option for a user.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Plan-Finding Logic Chains

This MCP server gives your agent the tools to run a full health insurance research sequence. Your chain can start by finding a user's location with `get_counties_by_zip`, then feed that county data into `search_plans` to get a list of available options. From there, the agent can iterate through the results, calling `get_plan_details` on the most promising plans. Because LangChain passes the output of one step to the next, you can build a logical funnel that narrows down dozens of plans to the two or three that actually fit a user's criteria.

Verify Coverage for Doctors and Drugs

Don't just find plans; confirm they actually work for the user. Give your agent the `search_providers` and `search_drugs` tools to identify specific doctors and medications. The agent can then use `get_provider_coverage` and `get_drug_coverage` to check if they're covered by a specific plan. This is where the agent's reasoning comes in. It can check a list of three must-have prescriptions against a plan's formulary and tell you if one of them isn't covered. You'll see the entire process in your LangSmith traces, step by step.

Analyze Year-Over-Year Plan Changes

Plans don't stay the same. The `get_plan_crosswalk` tool lets your agent check how a plan has changed from the previous year. This is critical for building agents that handle renewals. Your agent can spot if a plan is being discontinued or if its ID is changing, which often signals other shifts in coverage or cost. It's a simple but powerful MCP tool for avoiding surprises during open enrollment.

Setup guide

Set up HealthCare.gov 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 HealthCare.gov 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({
    "healthcaregov-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 HealthCare.gov 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 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 LangChain

Your agent should call `get_plan_details` for each of the two plan IDs. It can then parse the resulting JSON objects to extract and compare key fields like deductibles, out-of-pocket maximums, and monthly premiums.

The right way is a two-step chain. First, the agent calls `get_counties_by_zip` with the ZIP code to get the county FIPS code. Then, it uses that FIPS code in the `search_plans` tool to get accurate results for that specific market.

Yes. The agent would use `search_providers` to find the exact ID for your doctor. Then it would pass that provider ID and a plan ID to the `get_provider_coverage` tool to get a definitive yes or no on in-network coverage.

The HealthCare.gov API is updated for each enrollment period. If a plan is returned by `search_plans`, it's considered available. You can use `get_plan_crosswalk` to see how plans transition between years, which helps identify discontinued plans ahead of time.

The server only handles transient data like plan details, drug formularies, and provider networks from the public API. Each tool call is a stateless, ephemeral transaction processed in a V8 Isolate sandbox. Your LangChain agent initiates the request, and Vinkius ensures the connection is secure, but nothing is logged or stored on the MCP server itself.

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