How to Use the Modulr MCP in AutoGen

Q: How do I register Modulr MCP tools with AutoGen agents?

Install the extension using pip install -U "autogen-extmcp". Use the mcpservertools helper with your Vinkius HTTP URL to fetch the tool definitions, then pass that list directly to your AssistantAgent constructor.

Q: How do AutoGen agents track active Modulr account balances?

The agents query modulrgetaccounts at the start of their conversation loop. This ensures both the auditing agent and the execution agent are debating using the exact same real-time balance figures.

Deploy consensus-driven AutoGen agent teams to coordinate, review, and execute high-volume Modulr payments safely.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modulr MCP to AutoGen

Create your Vinkius account to connect Modulr 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 Modulr with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Account Creation

The `modulr_create_account` tool allows your AutoGen developer agent to spin up new GBP or EUR ledgers after gaining approval from your compliance agent. In this multi-agent setup, one agent requests the ledger while another verifies that the customer profile is fully onboarding-compliant. This collaborative check prevents unauthorized ledger creation. Once both agents agree that the parameters meet your compliance rules, the designated execution agent triggers the tool to establish the live account.

Multi-Agent Beneficiary Verification

Using the `modulr_create_beneficiary` tool, your AutoGen setup maps external recipients and IBANs only after your security agent completes an automated risk assessment over the MCP transport layer. Your security agent audits the destination routing details, while the operations agent confirms the transfer limits. By separating these duties, you eliminate single-point-of-failure risks in automated payouts. The tool is only called when the conversation reaches a verified consensus, protecting your company from fraudulent routing changes.

Debated Payment Execution via AutoGen MCP Server

The `modulr_create_payment` tool processes outgoing SEPA or Faster Payments after your agent team debates and approves the transaction details. A performance agent pushes for immediate execution while a risk agent validates the transaction history using `modulr_get_transactions`. This debate ensures that no massive payment array is processed blindly. Once they reach a consensus, the execution agent triggers the payout and reports the final settlement status to the group.

Setup guide

Set up Modulr 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 Modulr 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="Modulr_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the extension using `pip install -U "autogen-ext[mcp]"`. Use the `mcp_server_tools` helper with your Vinkius HTTP URL to fetch the tool definitions, then pass that list directly to your `AssistantAgent` constructor.

Yes. If the security agent detects anomalies during the debate phase, it can refuse to sign off on the conversation, preventing the execution agent from calling `modulr_create_payment`.

The agents query `modulr_get_accounts` at the start of their conversation loop. This ensures both the auditing agent and the execution agent are debating using the exact same real-time balance figures.

Yes. The MCP server handles concurrent requests efficiently, allowing your agent team to dispatch multiple payment instructions in parallel while maintaining strict order of operations.

Vinkius manages all Modulr API keys and HMAC signing secrets within hardware-isolated vaults. Your AutoGen agents never see or touch the raw secrets; they only interact with the high-level tools via secure, tokenized MCP channels.

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