How to Use the ChargeDesk MCP in AutoGen

Q: How do I start a billing debate between AutoGen agents about a ChargeDesk issue?

You'd set up at least two AssistantAgent instances with different system prompts and access to ChargeDesk tools. For instance, one agent's prompt could be "You are a cautious accountant," while another's is "You are a customer-focused support rep." Then you give them a task, and they'll start the conversation.

Q: Can an AutoGen agent ask for approval before refunding a ChargeDesk payment?

Absolutely. You can set up a UserProxyAgent that receives the refund proposal from another agent. The system will then pause and wait for your manual input in the terminal before the refundchargedeskpayment tool is actually executed.

Let your AutoGen agents debate the best way to handle billing issues. One agent finds the data, another suggests a refund, and a manager approves.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ChargeDesk MCP to AutoGen

Create your Vinkius account to connect ChargeDesk 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 ChargeDesk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Multi-Agent Billing Team

AutoGen lets you build a team of specialized AI agents that talk to each other. You can create a "Billing Analyst" agent that only has permission to use read-only tools like `list_chargedesk_charges` and `get_customer_details`. It finds the facts and reports them. Then, create a "Support Agent" that can propose actions, like using `refund_chargedesk_payment`. A third "Manager" agent reviews the conversation and gives the final approval. This MCP Server gives them the tools to work with, creating a secure, auditable workflow where no single agent has too much power.

Let Agents Debate Financial Actions

The real power of AutoGen is in conversation. Imagine a customer disputes a charge. One agent uses `get_charge_details` and argues it's valid based on usage logs. Another agent checks the customer's history with `get_customer_details` and argues for a goodwill refund to retain a valuable client. They debate until they reach a consensus, which is then passed to you or a manager agent for a final decision. You're not just executing a script; you're simulating a team discussion to arrive at a better, more nuanced outcome.

Configure Your AutoGen Team with ChargeDesk Tools

Setting this up is straightforward. You use the `mcp_server_tools` function to pull all the available ChargeDesk tools directly into your AutoGen environment. The `McpToolAdapter` handles the conversion automatically. From there, you assign specific tools to each of your agents. The `AssistantAgent` constructor takes a `tools` list, so you can precisely control which agent can list subscriptions with `list_chargedesk_subscriptions` and which one is allowed to process a `refund_chargedesk_payment`. This is how you enforce roles and permissions within your agent group.

Setup guide

Set up ChargeDesk 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 ChargeDesk 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="ChargeDesk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

When you define your agents, you'll pass a specific list of tools to each one. To create a read-only agent, only give it tools like `list_chargedesk_charges` and `get_customer_details`. Omit the `refund_chargedesk_payment` tool from its configuration.

Yes, each agent in the conversation can invoke tools. For example, one agent might call `list_chargedesk_subscriptions` while another calls `get_customer_details` for the same user. The results become part of the shared conversation history for all agents to see and react to.

You'd set up at least two `AssistantAgent` instances with different system prompts and access to ChargeDesk tools. For instance, one agent's prompt could be "You are a cautious accountant," while another's is "You are a customer-focused support rep." Then you give them a task, and they'll start the conversation.

Absolutely. You can set up a `UserProxyAgent` that receives the refund proposal from another agent. The system will then pause and wait for your manual input in the terminal before the `refund_chargedesk_payment` tool is actually executed.

The outputs of any tool calls, including customer names, subscription details, and charge information, are posted as messages in the conversation history. Since this data is visible to all participating agents, it's secured by your Vinkius token which gates access to the MCP server. The data itself is only transmitted over secure connections and isn't stored by Vinkius.

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