How to Use the Mercury MCP in AutoGen

Deploy a multi-agent team in AutoGen to debate and execute your Mercury banking tasks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to AutoGen

Create your Vinkius account to connect Mercury 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 Mercury with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate financial decisions in AutoGen

Assign one agent to monitor `get_treasury_balance` while another prepares to execute a payment. They discuss the current state before taking any action. This adds a layer of deliberation. If the balance is low, the security agent can halt the execution flow until a human reviews the request.

Automate team-based Mercury workflows

Let your agents coordinate the `list_team_members` and `list_payments` tools to audit internal spending. They work together to cross-reference data and flag discrepancies. Each agent has a specific role. You define the logic, and the agents negotiate the best way to extract and process the bank information.

Simplify schema management in AutoGen

The adapter handles the heavy lifting of converting tool schemas for your agents. You just define the agents and pass the tools list, and they immediately understand how to call `create_recipient`. You don't need to write custom wrappers. The integration maps the server tools into a format your agents can read and execute.

Setup guide

Set up Mercury 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 Mercury 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="Mercury_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You define different system prompts for each agent. They then use the available tools to gather evidence and propose actions in the conversation history.

Yes, you can define specific agents that only have access to read-only tools. This enforces a separation of duties within your agent team.

Every tool call and agent response is recorded in the conversation logs. You can audit these at any time to see exactly who did what.

The conversation stalls until the agents reach a consensus or you intervene. You can set up a human-in-the-loop agent to act as the final arbiter.

The server uses ephemeral sessions and secure transport. Your banking credentials and transaction records never touch the agent's memory outside of the immediate, encrypted task execution.

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