How to Use the Applied Epic MCP in AutoGen

Q: How do I register the Applied Epic tools in AutoGen?

Install the autogen-extmcp package. Use mcpservertools with your Vinkius HTTP endpoint, then pass the resulting list into your AssistantAgent constructor.

Q: Is it possible to restrict AutoGen agents to read-only Applied Epic tools?

Yes. You simply omit tools like createactivity when passing the list to your agents. They will only be able to debate over read-only data.

Deploy debating agents in AutoGen to audit insurance policies, review client risk, and log consensus decisions.

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 AutoGen

Create your Vinkius account to connect Applied Epic to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit policies with AutoGen teams

Complex insurance reviews require multiple perspectives. You can set up a compliance agent and a risk agent to jointly analyze active contracts by calling `list_policies`. When they spot a discrepancy, the agents debate the next step. One might trigger `list_lines` to check the specific General Liability limits, while the other reviews the overall policy structure. They do not stop until they reach a consensus.

Cross-reference client details

Autonomous teams need access to the underlying customer data. An agent calls `get_client` to fetch the primary record while a secondary agent runs `list_attachments` to look for missing signed forms. This setup prevents single-agent errors. If the first model misinterprets the client's status, the second model challenges the finding based on the attachment metadata. The MCP Server feeds them the raw facts they need to argue effectively.

Execute decisions after deliberation

Once your agents agree on a course of action, they can actually do something about it. The system uses `create_activity` to log their final recommendation directly into the agency management platform. Before starting a massive audit run, the lead agent will typically call `get_account_check` to verify the connection is healthy. If it fails, the agent alerts the team rather than failing silently mid-process.

Setup guide

Set up Applied Epic MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Applied Epic tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Applied Epic_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Applied Epic data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Applied Epic_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Applied Epic data")
    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 AutoGen

Install the autogen-ext[mcp] package. Use mcp_server_tools with your Vinkius HTTP endpoint, then pass the resulting list into your AssistantAgent constructor.

They can. The McpToolAdapter converts the schemas so any agent in your chat can call `list_clients` or `get_policy` if they have the right permissions.

The agents read the tool schemas and manage pagination parameters automatically. If they need to pull a massive list via `list_activities`, they will iterate through the pages as part of their conversation loop.

Yes. You simply omit tools like `create_activity` when passing the list to your agents. They will only be able to debate over read-only data.

Very secure. Vinkius operates on a zero-trust model. When your agents pull sensitive policy limits or client activity logs, the data moves through an isolated container that spins down the second the operation completes.

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