How to Use the Chargeblast MCP in AutoGen

Q: How do I register Chargeblast tools with my AutoGen agents?

Install autogen-extmcp. Use mcpservertools with your Vinkius HTTP endpoint, then pass the resulting list into your AssistantAgent constructor. The adapter handles the schema translation.

Deploy a team of AutoGen agents to debate and resolve your chargeback alerts automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chargeblast MCP to AutoGen

Create your Vinkius account to connect Chargeblast 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 Chargeblast with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents debate dispute validity

Build a fraud analyst agent that pulls active threats using `list_dispute_alerts`. Resolving chargebacks is rarely a black-and-white decision. It hands the raw data to a financial risk agent, which argues whether fighting the claim is worth the associated fees. They argue the case based on historical data. The analyst might pull specific transaction context via `get_dispute_alert_details` to prove the customer received the item. Once they reach a consensus, the lead agent decides whether to accept or challenge the dispute.

Execute decisions after consensus

Once your agents agree an alert is valid, one of them triggers `update_alert_status` to refund the customer immediately. Talk is cheap unless the system can actually enforce the outcome through an MCP tool. This stops the chargeback dead in its tracks. If the system detects a billing error on the provider side, an agent can fire `request_dispute_credit`. You get the benefit of deliberate, multi-perspective reasoning combined with instant execution.

Feed AutoGen real merchant data

One agent can monitor your database and run `upload_order_data` whenever a new purchase occurs. Your agents need context from your MCP Server to make good arguments. This primes the deflection network before any disputes even register. Another agent can periodically call `list_deflection_logs` to audit how many chargebacks were actually prevented. It summarizes the blocked attempts and posts a report to your Slack channel, proving the system works.

Setup guide

Set up Chargeblast 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 Chargeblast 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="Chargeblast_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp]. Use mcp_server_tools with your Vinkius HTTP endpoint, then pass the resulting list into your AssistantAgent constructor. The adapter handles the schema translation.

Yes. You can provide the same tool list to your risk agent and your execution agent. They will both route their function calls through the same active session.

If an upload fails, the executing agent receives the error text. It will usually discuss the failure with the group, correct the payload formatting, and try the request again.

For managed connections, use the StreamableHttpServerParams configuration. This maintains a persistent link for your agents during their conversation.

Not a chance. Your instance runs in a completely isolated sandbox. Dispute reasons, credit card network metadata, and refund amounts are processed securely and never persisted on our infrastructure.

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