How to Use the Craftboxx MCP in AutoGen

Q: Give me an example of an AutoGen and Craftboxx conversation.

A 'planner' agent could propose a job, then a 'resourcechecker' agent could use listmaterials to flag a low-stock item. A 'manager' agent could then weigh in, deciding whether to proceed or use createorder to restock first.

Q: How do I connect my AutoGen agents to the Craftboxx MCP Server?

After installing the autogen-extmcp package, you use the mcpservertools function with your Vinkius server URL. This returns a list of tools that you can directly assign to your AssistantAgent's configuration.

Assemble a team of AutoGen agents to debate and manage your Craftboxx operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craftboxx MCP to AutoGen

Create your Vinkius account to connect Craftboxx 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 Craftboxx with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Your Agents Debate the Best Plan

Don't just run one task. With AutoGen, you create a team of agents that talk to each other to solve a problem. One agent can act as a dispatcher, using `list_appointments` to find a scheduling conflict. It then presents this to another agent acting as a manager. The 'manager' agent can then ask a 'logistics' agent to check inventory with `list_materials` and vehicle availability with `list_vehicles_resources` before deciding on a solution. The final plan comes from a consensus, not a single command.

Simulate Your Real-World Team

You can assign specific Craftboxx tools to different agents to mirror your actual team structure. Give your 'finance' agent access to `get_business_stats`, while your 'field ops' agent can only use `list_tasks` and `get_order_details`. This lets them act within their roles. This helps you build systems that handle complex scenarios. When a new job is created with `create_order`, multiple agents can discuss who should take it, what they'll need, and how it impacts the schedule. It's a way to test out decisions before they affect your real-world team.

Give Your AutoGen Team Operational Tools

This MCP server is the bridge between your agent conversations and your actual business data in Craftboxx. When agents debate a course of action, they use these tools to ground their arguments in facts, not guesses. An agent can't just claim a resource is available; it has to prove it by calling `list_vehicles_resources` and showing the result to the other agents. This makes your multi-agent system more reliable because it's tied to the reality of your day-to-day operations.

Setup guide

Set up Craftboxx 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 Craftboxx 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="Craftboxx_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

AutoGen lets you build a team of specialized AI agents that collaborate. They can debate the best way to schedule a job or manage inventory, using Craftboxx tools to pull real data and justify their decisions to each other.

Yes. You can configure each agent with access to a specific subset of the Craftboxx tools. For example, a 'billing' agent could access `get_business_stats` while a 'dispatcher' agent uses `list_appointments` and `list_employees`.

A 'planner' agent could propose a job, then a 'resource_checker' agent could use `list_materials` to flag a low-stock item. A 'manager' agent could then weigh in, deciding whether to proceed or use `create_order` to restock first.

After installing the `autogen-ext[mcp]` package, you use the `mcp_server_tools` function with your Vinkius server URL. This returns a list of tools that you can directly assign to your AssistantAgent's configuration.

The agents only access the specific Craftboxx data needed for their discussion, like order details, employee lists, or business stats. Vinkius ensures each tool call is executed in a separate, ephemeral sandbox, so your operational data remains isolated and is not stored after the call.

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