How to Use the Highnote MCP in AutoGen

Q: How do I load the Highnote MCP Server into AutoGen?

You install autogen-extmcp and initialize mcpservertools. Pass your HTTP URL using StreamableHttpServerParams and hand the tools to your AssistantAgent.

Q: Can AutoGen agents debate Highnote card products?

Yes. One agent can call listcardproducts to pull the available fleet and consumer options. The agents then discuss which program fits the current user request.

Q: Do I need to convert the API schemas for AutoGen?

No. The McpToolAdapter automatically converts the JSON schemas from the MCP server into a format the agents understand.

Give your AutoGen agents access to Highnote so they can debate and execute card status updates based on real financial data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Highnote MCP to AutoGen

Create your Vinkius account to connect Highnote 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 Highnote with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Transaction Review

The `list_financial_transactions` tool supplies raw spending data to your AutoGen discussion group. You assign one agent to pull the recent processing history. A second agent, acting as a security auditor, reviews the output to flag irregular patterns in the merchant codes. When the security agent finds an anomaly, it requests more context. The first agent calls `get_transaction_details` to grab the specific metadata. They debate the risk level before presenting a final recommendation to you.

Highnote MCP Server for Ledger Audits

The `list_ledger_entries` tool gives your agents the exact inputs they need to argue about reconciliation. An accounting agent pulls the individual entries for a specific financial account. A compliance agent challenges the categorization of those entries based on internal rules. If they disagree on an account's standing, they pull the current balance using `get_financial_account`. The agents negotiate until they reach a consensus on the exact discrepancy. You get a resolved audit trail instead of a raw data dump.

Consensus-Driven Card Freezes

The `update_card_status` tool lets your agent group physically alter a card's state to ACTIVE, FROZEN, or CLOSED. You build a workflow where no single agent can execute a freeze. A fraud agent proposes the action, and a support agent verifies the user impact via `list_payment_cards`. Before the final call, the system checks the user's identity using `list_account_holders`. Once both agents agree the threat is real and the target is correct, the system pushes the status change. You automate security without sacrificing accuracy.

Setup guide

Set up Highnote 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 Highnote 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="Highnote_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Highnote 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="Highnote_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Highnote 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 Highnote. 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 Highnote 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 Highnote MCP in AutoGen

You install `autogen-ext[mcp]` and initialize `mcp_server_tools`. Pass your HTTP URL using `StreamableHttpServerParams` and hand the tools to your `AssistantAgent`.

Yes. One agent can call `list_card_products` to pull the available fleet and consumer options. The agents then discuss which program fits the current user request.

No. The `McpToolAdapter` automatically converts the JSON schemas from the MCP server into a format the agents understand.

Yes. Any agent in your group with access to the tools can execute calls. They share the results in the common conversation thread.

The server accesses personally identifiable information and exact account balances. The MCP protocol keeps this data inside an isolated sandbox, ensuring your agents only access what they need through a single, secure endpoint token.

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