How to Use the Mambu MCP in AutoGen

Q: Can I limit which AutoGen agents have access to Mambu tools?

Yes, you can register tools like getloanaccount only with specific agents in your AutoGen configuration. You might give your risk assessment agent full access to loan details while restricting your customer-facing communication agent to listcommunications. This enforces strict role-based access control within your multi-agent system.

Build consensus-driven AutoGen agents that audit Mambu ledger records over a secure MCP connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mambu MCP to AutoGen

Create your Vinkius account to connect Mambu 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 Mambu with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent loan underwriting in AutoGen

`get_loan_account` provides the raw financial foundation for your AutoGen multi-agent credit assessment conversations. An AutoGen risk-auditing agent calls this Mambu tool to inspect outstanding liabilities, while a separate compliance agent reviews active accounts to flag potential exposure. These agents debate the Mambu risk profile within the AutoGen framework before approving a credit limit change. The discussion is grounded in live data from `list_loan_accounts`, preventing any single AutoGen agent from making unilateral decisions based on outdated balances.

Automate deposit auditing with AutoGen MCP Server

`list_deposit_accounts` allows your specialized AutoGen financial agents to monitor corporate deposit balances and flag anomalous activity. An AutoGen performance agent tracks interest accruals while an audit agent cross-references these figures against Mambu transaction histories. By using Mambu `get_deposit_account`, the AutoGen agents drill down into specific high-value accounts during their debate. They compare current Mambu balances against historic trends to verify that deposit holdings match the client's declared risk profile.

Resolve back-office banking tasks through agent debate

`list_tasks` exposes operational bottlenecks to your AutoGen agent team, allowing them to coordinate and assign follow-up Mambu actions. One AutoGen agent identifies overdue tasks, while another queries Mambu `list_communications` to see if the customer was already notified. Once the AutoGen agents agree on the next step, they update the task status using the core Mambu ledger tools. This collaborative workflow ensures that complex Mambu operational issues, like missing loan documents, are resolved through programmatic consensus rather than manual tracking.

Setup guide

Set up Mambu 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 Mambu 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="Mambu_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen uses a conversational interface where agents take turns executing tools like `list_transactions` and sharing the results. For example, an analyst agent retrieves the transaction list and presents it to an auditor agent, who then decides if a call to `get_client` is required to verify the user's identity. This collaborative flow ensures thorough verification of Mambu ledger activities.

Yes, you can register tools like `get_loan_account` only with specific agents in your AutoGen configuration. You might give your risk assessment agent full access to loan details while restricting your customer-facing communication agent to `list_communications`. This enforces strict role-based access control within your multi-agent system.

When agents retrieve conflicting states—such as a pending task in `list_tasks` contradicting a completed transaction in `list_transactions`—they enter a debate loop. The coordinator agent parses both tool outputs, logs the discrepancy, and requests human intervention or executes a fresh query to resolve the conflict. This prevents automated errors from silently corrupting your Mambu banking workflows.

The MCP server supports both stdio and Streamable HTTP transports, allowing your AutoGen agents to connect across local and cloud environments. It runs inside the secure Vinkius V8 isolate sandbox, ensuring that all API calls are executed with sub-millisecond overhead and zero persistent storage.

Your customer details, loan balances, and transaction histories are protected by the zero-trust architecture of the Vinkius sandbox. AutoGen agents only process these data points in-memory during their conversation, and the underlying MCP server never caches or exports your core Mambu ledger records. This ensures that sensitive banking data remains strictly within your authorized session boundaries.

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