How to Use the Recurly MCP in AutoGen

Q: Can AutoGen agents resolve billing disputes using Recurly?

Yes, your agents can use listtransactions and getinvoice to investigate customer complaints. They analyze the payment history, debate the cause of the failure, and draft a resolution. This automates the first line of billing support.

Q: How do AutoGen agents handle missing Recurly parameters?

If an agent tries to call getaccountdetails without an account code, the partner agents will point out the missing parameter in the chat. They will ask the user or query listbillingaccounts to find the correct identifier. The conversation continues once they have the required data.

Run autonomous billing debates and consensus-driven subscription management with Recurly and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Recurly MCP to AutoGen

Create your Vinkius account to connect Recurly 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 Recurly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent billing tasks via this MCP Server

The Recurly MCP Server enables multi-agent negotiation over your subscription workflows. One agent can draft an onboarding flow using `create_billing_account` while a supervisor agent checks the parameters. They discuss the data structure before executing the live API call. This collaborative approach prevents formatting errors in your customer database. The agents use `get_account_details` to check existing records before creating duplicates. You get clean, human-like decision making without writing complex validation scripts.

Run consensus-driven audits with AutoGen and Recurly

This MCP Server exposes `list_billing_invoices` and `list_transactions` for automated reconciliation. You set up an auditor agent to flag unpaid invoices and a collections agent to draft follow-up emails. They cross-reference the data until they agree on the outstanding balance. The debate happens autonomously in the background. If the auditor agent finds a discrepancy, it calls `get_invoice` to inspect the line items. Once both agents reach a consensus, they present the finalized report to your team.

Optimize subscription retention using AutoGen agents

The integration allows your agents to analyze churn risk using `list_subscriptions` and `get_subscription_details`. A retention agent reviews expiring accounts and proposes discount strategies. It queries `list_coupons` to find an appropriate incentive to offer the customer. The strategy agent then debates whether the discount makes financial sense. They look at the revenue impact using `get_revenue_summary` before making a final offer. This ensures your automated retention campaigns are both aggressive and profitable.

Setup guide

Set up Recurly 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 Recurly 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="Recurly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the MCP tool adapter to convert the Vinkius server tools into the format AutoGen expects. Pass this list directly to your AssistantAgent constructor during initialization. The agents can then call tools like `list_subscription_plans` during their conversations.

Yes, your agents can use `list_transactions` and `get_invoice` to investigate customer complaints. They analyze the payment history, debate the cause of the failure, and draft a resolution. This automates the first line of billing support.

The server supports both stdio and Streamable HTTP transports. For multi-agent environments, we recommend the HTTP transport hosted on Vinkius. This allows multiple distributed agents to access the billing tools simultaneously.

If an agent tries to call `get_account_details` without an account code, the partner agents will point out the missing parameter in the chat. They will ask the user or query `list_billing_accounts` to find the correct identifier. The conversation continues once they have the required data.

Your credentials reside safely in the Vinkius vault, injected only at runtime into isolated V8 sandboxes. No agent can access or leak the raw API keys. Every transaction, subscription status, and invoice detail is processed securely without persistent logging.

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