How to Use the Customers.ai MCP in AutoGen

Q: How does AutoGen handle conflicting updates to a Customers.ai contact?

The agents must reach a consensus before calling updatecontactattributes. This prevents race conditions where two agents try to write different data to the same contact profile.

Let your AutoGen agents debate and coordinate on lead generation, visitor tagging, and automated outreach strategies.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customers.ai MCP to AutoGen

Create your Vinkius account to connect Customers.ai 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 Customers.ai with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven visitor triage and tagging

`list_xray_leads` feeds newly identified website visitors to an AutoGen group chat where multiple agents decide how to handle them. While a marketing agent evaluates the lead quality, a sales agent checks if they are already in the CRM using `search_contacts`. This setup works natively with the MCP Server. Once they agree on a classification, a database agent calls `add_tag_to_contact` to apply the correct tag. Debating these classifications means you don't spam unqualified visitors with irrelevant messages.

Collaborative outreach campaigns using AutoGen

`send_text_message` fires off targeted SMS texts only after your AutoGen agents reach a consensus on the copy. First, one agent drafts the message, then a compliance agent checks it for tone, and a third agent executes the tool. Running this via the Customers.ai MCP Server keeps your orchestration logic clean. Schema conversion happens behind the scenes, allowing your agents to focus on negotiating the best outreach strategy.

Automated profile updates through agent negotiation

`update_contact_attributes` modifies contact profiles based on structured decisions made by your AutoGen team. If a visitor performs a specific action, the agents debate which attributes need updating before writing to the contact card. Whenever the agents need more context, they call `get_contact` to review the current profile. This collaborative loop ensures your database is only updated with verified, clean data.

Setup guide

Set up Customers.ai 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 Customers.ai 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="Customers.ai_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You use the Customers.ai MCP Server adapter to convert the server's tools into a format AutoGen understands. Then, you pass this list directly to your AssistantAgent constructor.

Yes, you can configure your group chat so that a supervisor agent must approve the message draft before the execution agent calls the tool.

The agents must reach a consensus before calling `update_contact_attributes`. This prevents race conditions where two agents try to write different data to the same contact profile.

Yes, the server supports streamable HTTP transport. This allows your AutoGen agents to receive tool execution states in real-time during their conversation.

All communication between AutoGen and the Customers.ai API is encrypted in transit. The V8 sandbox ensures that visitor details and phone numbers are processed in a secure, ephemeral 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