How to Use the Bolt MCP in AutoGen

Let your AutoGen agents debate and execute payment actions using the Bolt 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 Bolt MCP to AutoGen

Create your Vinkius account to connect Bolt 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 Bolt with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate refunds with AutoGen

Set up a finance agent and a support agent to negotiate a refund using `refund_transaction`. One agent checks the policy, while the other verifies the transaction details. This ensures that refunds only happen after both agents reach a consensus. It adds a layer of human-like deliberation to your automated payment processes.

Capture transactions using AutoGen agents

Use `capture_transaction` within a multi-agent group to finalize payments. One agent initiates the capture, while a watchdog agent verifies the transaction amount matches the order. This prevents errors by having a second agent audit the input before the tool executes. The agents reconcile the data, ensuring the capture is valid.

Void payments with AutoGen deliberation

Deploy `void_transaction` through a consensus-based workflow. If the system detects a duplicate order, the agents discuss the necessity of the void before calling the tool. It turns a simple API call into a verified business decision. You define the logic, and the agents handle the debate to reach the correct conclusion.

Setup guide

Set up Bolt 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 Bolt 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="Bolt_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You pass the tool list from the server to your AssistantAgent. The agents then decide which tool to call based on the task description you provide.

Yes, the agents include the tool outputs in their message history. This allows them to challenge or build upon the data retrieved from the server.

The adapter handles both stdio and HTTP. You configure the server parameters in your agent setup and the communication happens automatically.

The server manages stateful sessions effectively. Each agent in your group gets the current tool schema so they can participate in the decision process.

The data exchanged between agents is limited to what the tools return. We enforce strict isolation so your sensitive transaction IDs remain inside your controlled agent environment.

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