How to Use the Konfío MCP in AutoGen

Q: How can I get my AutoGen agents to use the Konfío tools?

Install the autogen-extmcp package. Then, use the mcpservertools function with your Vinkius MCP server URL. This returns a list of tools you can pass directly to your AssistantAgent constructors.

Q: Can multiple AutoGen agents use different Konfío tools at once?

Yes, that's the point. You can create one agent with createinvoice to handle billing and another with makeloanpayment to manage debt. They can then talk to each other to coordinate financial activities.

Q: How would an AutoGen team decide whether to request more credit from Konfío?

You could set up a team. An "AnalystAgent" would use checkcreditstatus and listloans to assess the current situation. A "GrowthAgent" might argue for using requestcreditline for expansion. They would debate until they reach an agreement you approve.

Assemble a team of AutoGen agents to debate and manage your Konfío finances.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Konfío MCP to AutoGen

Create your Vinkius account to connect Konfío 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 Konfío with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Financial Oversight

Don't just execute tasks—deliberate them. You can create a "FinanceAgent" that proposes paying a bill with `create_transfer` and a "ComplianceAgent" that double-checks the associated invoice with `list_invoices` before giving approval. The agents connected to this MCP server converse and reach a consensus before acting. This approach catches errors before they happen. Imagine a "CreditAgent" suggests using `request_credit_line`. A "RiskAgent" could then step in, use `check_credit_status` and `list_loans` to analyze current debt, and argue against taking on more. The final decision is smarter because it's been challenged.

Automate Complex Financial Decisions

Some financial questions don't have a simple answer. Use an AutoGen team to tackle them. One agent can pull credit card data using `list_cc_transactions`, another can fetch loan payment schedules with `get_payment_schedule`, and a "ManagerAgent" can synthesize their findings to recommend a budget. This is about simulating a real finance team. Each agent, equipped with specific Konfío tools, brings its piece of the puzzle to the conversation. The final output is a plan that has been vetted from multiple angles.

Build a Conversational MCP Server Team

Getting started is quick. You use `mcp_server_tools` to load all 14 Konfío functions directly into your AutoGen workspace. Then you can assign different tools to different `AssistantAgent` instances, giving each one a specific role. For example, give your "InvoicingClerk" agent just the `create_invoice` and `list_invoices` tools. This limits its scope and makes the overall system more robust. The `McpToolAdapter` handles all the schema conversions, so the agents can focus on the conversation.

Setup guide

Set up Konfío 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 Konfío 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="Konfío_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Then, use the `mcp_server_tools` function with your Vinkius MCP server URL. This returns a list of tools you can pass directly to your `AssistantAgent` constructors.

Yes, that's the point. You can create one agent with `create_invoice` to handle billing and another with `make_loan_payment` to manage debt. They can then talk to each other to coordinate financial activities.

You could set up a team. An "AnalystAgent" would use `check_credit_status` and `list_loans` to assess the current situation. A "GrowthAgent" might argue for using `request_credit_line` for expansion. They would debate until they reach an agreement you approve.

It's a perfect fit. You can have your agent team debate a course of action—like which loan to pay off first—and then present their recommendation to a `UserProxyAgent`. You give the final "yes" or "no" before any tool like `make_loan_payment` is actually executed.

Only the agents you authorize. Data like loan details or invoice contents are fetched by the MCP server inside a temporary, zero-trust environment for a specific agent's request. Your Vinkius token secures access, and the data is not stored after 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