How to Use the Customerly MCP in AutoGen

Let your AutoGen agents debate and manage Customerly. Build multi-agent systems that create users, manage tags, and analyze conversations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customerly MCP to AutoGen

Create your Vinkius account to connect Customerly 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 Customerly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven User Management

Don't just `create_update_user`. Have multiple agents decide if it's the right move. A "SalesAgent" could propose creating a lead, while a "DataQualityAgent" checks if the email is valid before the `create_update_lead` tool is ever called. This approach prevents errors. You can build a system where one agent proposes using `delete_user`, but a "RetentionAgent" has to approve it after checking conversation history with `get_conversation`. The final action is a result of negotiation.

Multi-Agent Conversation Analysis

Set up a team of agents to analyze your support queue. One agent uses `list_conversations` to get the queue. A "TriageAgent" reads each one with `get_conversation` and assigns a priority. A "ProductAgent" scans for feature requests. The agents talk to each other to get the job done. The TriageAgent might ask the ProductAgent, "Is this a bug or a feature request?" before deciding how to tag the conversation. You're modeling a human team's workflow.

Debate-Based Tagging with this MCP Server

Tagging users isn't always simple. Should a new user be tagged as "trial" or "demo_request"? Let your AutoGen agents decide. One agent can argue for "trial" based on signup source, another can argue for "demo_request" based on a form submission. The agents will debate until they reach a conclusion, then one of them executes the `add_tag` tool with the agreed-upon tag. This ensures your Customerly data stays consistent and reflects a consensus, not just a single agent's guess.

Setup guide

Set up Customerly 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 Customerly 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="Customerly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign the Customerly tools to one or more agents. For example, give a "UserAdminAgent" the `create_update_user` tool, and a "SupportAgent" the `list_conversations` tool. They can then call each other to get tasks done.

Yes, this is a core AutoGen pattern. An agent proposes calling `delete_user`, and a UserProxyAgent asks you for confirmation before it's executed. You can also have another agent provide automated approval.

Create an agent that monitors for new leads. When one appears, it can start a conversation with other agents to decide on the correct tags, then use the `add_tag` tool to apply them.

You can build a very sophisticated one. One agent could handle the initial conversation, while another agent in the background uses `list_users` to look up the customer's details and provide context.

Data is passed through the Vinkius MCP Server endpoint. Within your AutoGen application, data like user emails or conversation text is shared between agents as they converse. The entire process runs in your environment, and Vinkius doesn't log or store the content of these messages.

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