How to Use the Belvo MCP in AutoGen

Q: How do I load Belvo tools into an AutoGen agent using an MCP Server?

Install the autogen-extmcp package. Fetch the tools using mcpservertools with your Vinkius HTTP endpoint, then pass them into the AssistantAgent constructor.

Give your AutoGen agents direct access to Latin American banking APIs via the Belvo MCP Server to debate financial decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Belvo MCP to AutoGen

Create your Vinkius account to connect Belvo 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 Belvo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate on Belvo MCP Server data

Triggering `list_incomes` feeds raw salary data to a risk assessment agent while a loan approval agent reviews the same payload. They argue over debt-to-income ratios before issuing a final decision. Single agents miss obvious red flags. When one agent pulls data via `list_transactions`, another agent acts as an auditor to spot irregular spending patterns. The conversation forces a deeper analysis of the financial history.

Coordinate complex banking workflows

Firing `list_links` lets a diagnostic agent check connection health across multiple banks. If a link shows errors, a secondary agent automatically executes `get_link` to grab the specific failure codes. Delegating tasks speeds up the entire pipeline. One agent handles the broad `list_accounts` query, then assigns specific `get_account` deep-dives to worker agents. They report back to the manager agent with a consolidated summary.

Negotiate portfolio strategies

Fetching asset data with `get_investments` kicks off a strategy session between conservative and aggressive trading agents. They use the current holdings to argue about rebalancing needs. Cash flow matters during these debates. An agent pulling `list_balances` and `list_recurring_expenses` will push back against risky investments if the user's monthly burn rate is too high. Consensus requires checking all the numbers.

Setup guide

Set up Belvo 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 Belvo 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="Belvo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext[mcp] package. Fetch the tools using mcp_server_tools with your Vinkius HTTP endpoint, then pass them into the AssistantAgent constructor.

Yes. Any agent configured with the tool list can invoke the endpoints. They share the same underlying Vinkius connection to prevent rate limits.

The McpToolAdapter automatically translates the API schema. Your agents see native Python dictionaries when inspecting the transaction payloads.

Scripts execute blindly. AutoGen agents discuss the data, flag anomalies in account balances, and challenge assumptions before finalizing a financial report.

Only your local environment. Vinkius processes the authentication tokens ephemerally, ensuring sensitive transaction histories remain private to your specific agent chat.

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