How to Use the Applied Epic MCP in LangChain

Q: Can LangChain agents read past interaction logs in Applied Epic?

Yes. Your agent uses listactivities to pull historical tasks and logs for any account. This gives the model context on previous conversations before it acts.

Q: How do I verify my Applied Epic credentials in LangChain?

Run a quick test chain. Have your agent call getaccountcheck to confirm the connection is active before running larger batch jobs on your client list.

Wire your insurance workflows into LangChain to pull policies, track renewals, and log activities automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Applied Epic MCP to LangChain

Create your Vinkius account to connect Applied Epic 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 Applied Epic with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain client data in LangChain

Your ReAct agents need context before they take action. Connecting this MCP Server lets your agent run `list_clients` to find specific policyholders across your database. Once the agent identifies the target, it calls `get_client` to pull down the full record. The output of that tool feeds directly into the next step of your chain, letting you pass live insurance data into templates or downstream APIs.

Inspect policies and lines of business

Agents can audit coverage by running `list_policies` to grab active insurance contracts. When a specific contract needs review, the agent calls `get_policy` for the exact details. Multi-step reasoning works best when the agent can dig deeper. If a commercial account looks complex, LangChain triggers `list_lines` to break out Workers Comp, General Liability, and other specific coverages attached to that policy ID.

Log activities from agent outputs

Reading data is only half the job. After your pipeline finishes processing a renewal or compliance check, it calls `create_activity` to log the interaction back into the system. You can also track what happened previously. The agent runs `list_activities` to read past task logs or calls `list_attachments` to find documents linked to the account. Everything gets traced in LangSmith so you know exactly which tools fired.

Setup guide

Set up Applied Epic 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 Applied Epic 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({
    "applied-epic-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 Applied Epic 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 Applied Epic. 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 Applied Epic 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 Applied Epic MCP in LangChain

Install the langchain-mcp-adapters package. Pass your Vinkius endpoint to MultiServerMCPClient and call get_tools() to feed the operations to your ReAct agent.

Yes. Your agent uses `list_activities` to pull historical tasks and logs for any account. This gives the model context on previous conversations before it acts.

It does. Every time the agent queries a policy or creates an activity, LangSmith logs the exact input, output, and latency. You see exactly how the model reasoned through the insurance data.

Run a quick test chain. Have your agent call `get_account_check` to confirm the connection is active before running larger batch jobs on your client list.

Vinkius isolates every session in an ephemeral V8 sandbox. When your agent pulls policy details, client names, or coverage lines, that data passes through a zero-trust tunnel. Nothing gets stored 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