How to Use the Constructor MCP in AutoGen

Q: Can AutoGen agents search Constructor products?

Yes, they call the searchproducts tool to inspect CRM records inside the Headless Constructor.io platform. The agents then discuss the search results to pick the best product for the user.

Q: How do AutoGen agents use Constructor recommendations?

The agents trigger the getrecommendations tool to fetch cloud logging tracing vault limits. They negotiate how to distribute recommendations without exceeding these limits.

Q: Does AutoGen support Constructor custom search via MCP?

Yes, agents use the customsearch tool to identify precise active arrays spanning native hold parsing. This lets them resolve search conflicts during multi-agent planning.

Q: How do agents filter products by size?

They call the searchfiltered tool to get bounding JSON structures restricted to exact colors or sizes. The agents then filter out any items that do not match the user's criteria.

Let your AutoGen agents debate and resolve Constructor parameters autonomously with this 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 Constructor MCP to AutoGen

Create your Vinkius account to connect Constructor 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 Constructor with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve Constructor billing rules in AutoGen

The `search_sorted` tool enumerates explicitly attached structured rules exporting active billing configurations to your AutoGen conversation. The billing agent uses these rules to challenge the pricing recommendations proposed by the sales agent. This collaborative debate ensures that no transaction violates active billing contracts. AutoGen agents reach consensus on pricing before executing any final checkout actions.

Debate brand plan math using the MCP Server

The `browse_brand` tool inspects deep internal arrays mitigating specific plan math within the agent conversation. A performance agent analyzes these arrays to flag efficiency risks, while a marketing agent defends the brand placement. They negotiate the optimal brand display order based on actual contract math. The final agreed configuration is then dispatched to your frontend application.

Extract active account logic

The `autocomplete` tool extracts structural properties driving active account logic during agent planning phases. Your security agent reviews these properties to confirm the current user session has permission to view specific account details. By verifying these properties mid-conversation, AutoGen prevents unauthorized data disclosure. The agents halt execution if the extracted logic indicates a permission mismatch.

Setup guide

Set up Constructor 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 Constructor 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="Constructor_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Yes, they call the `search_products` tool to inspect CRM records inside the Headless Constructor.io platform. The agents then discuss the search results to pick the best product for the user.

The agents trigger the `get_recommendations` tool to fetch cloud logging tracing vault limits. They negotiate how to distribute recommendations without exceeding these limits.

Yes, agents use the `custom_search` tool to identify precise active arrays spanning native hold parsing. This lets them resolve search conflicts during multi-agent planning.

They call the `search_filtered` tool to get bounding JSON structures restricted to exact colors or sizes. The agents then filter out any items that do not match the user's criteria.

This MCP Server runs inside a secure, zero-trust V8 sandbox on Vinkius. All search history and customer bindings are processed ephemerally in memory and are destroyed as soon as the AutoGen conversation terminates.

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