How to Use the MoonClerk MCP in AutoGen

Q: How do I register the MoonClerk MCP Server tools in AutoGen?

Use the mcpservertools function from the autogen-ext package to load the tools. Pass the resulting tool list to your AssistantAgent constructor to enable them.

Q: How do AutoGen agents handle conflicting MoonClerk data?

They debate the tool outputs. For example, if listpayments shows a failed charge but the customer claims they paid, the agents will flag this discrepancy for human review.

Let AutoGen agents debate and resolve MoonClerk billing discrepancies autonomously using our MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoonClerk MCP to AutoGen

Create your Vinkius account to connect MoonClerk 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 MoonClerk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve billing issues with AutoGen agents

The `get_payment` tool provides transaction details that your AutoGen agents use during multi-agent debates to verify charges. If a customer disputes a charge, a support agent and a compliance agent analyze the raw payment data together to reach a consensus. This cooperative approach ensures that billing decisions are thoroughly vetted before any response is drafted. The agents negotiate based on the actual transaction history fetched directly from the MoonClerk API.

Audit subscriber status via MCP Server consensus

The `get_subscription` tool retrieves active plan details so your AutoGen agents can verify account standings. A security agent can cross-reference the output of this tool with access logs, while a customer success agent checks if the user is due for an upgrade. This automated deliberation prevents mistakes that a single agent might make. By discussing the subscription details, the group of agents determines the best path forward for the customer.

Analyze payment plans cooperatively

The `list_plans` tool exposes your available pricing tiers to the agent group for automated catalog analysis. Your product agent can propose a plan shift, while the finance agent reviews the plan details to ensure it aligns with company rules. This removes the need for manual intervention when analyzing pricing structures. The agents work through the plan options autonomously, using the live API data to make accurate recommendations.

Setup guide

Set up MoonClerk 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 MoonClerk 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="MoonClerk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the mcp_server_tools function from the autogen-ext package to load the tools. Pass the resulting tool list to your AssistantAgent constructor to enable them.

Yes, any agent in the AutoGen group chat can trigger tools like `get_customer` when the conversation requires real-time billing data to proceed.

They debate the tool outputs. For example, if `list_payments` shows a failed charge but the customer claims they paid, the agents will flag this discrepancy for human review.

Yes, you can connect to the Vinkius hosted server using StreamableHttpServerParams to stream tool execution results directly to your agents.

Vinkius runs the server in an isolated, zero-trust environment. Your billing records, payment forms, and plans are accessed strictly via secure runtime calls and are never cached or logged permanently.

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