How to Use the Clientjoy MCP in AutoGen

Let your AutoGen agents debate and manage your Clientjoy sales strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clientjoy MCP to AutoGen

Create your Vinkius account to connect Clientjoy 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 Clientjoy with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up Multi-Agent CRM Teams

This server gives your AutoGen agents the data they need to take on different roles. Create a "Sales Ops" agent that uses `list_leads` and `list_sales_proposals` to monitor the pipeline. At the same time, a "Finance" agent can use `list_billing_invoices` to track revenue and payments. These specialized agents can work together as a team. Each one focuses on its own metrics from Clientjoy, bringing a unique perspective to the conversation. It's like having a virtual team meeting where everyone comes prepared with real data.

Drive Decisions Through Conversation

The real power of AutoGen is unlocked when your agents start talking to each other. The Sales Ops agent might propose pursuing a big new lead. But the Finance agent, after using `get_customer_details` and seeing a history of late payments, can object and present the financial risk. This isn't a simple script; it's a debate. The agents use the data from the Clientjoy tools as evidence to support their arguments, helping you reach a more balanced decision. You're not just getting an answer; you're getting a consensus forged from different viewpoints.

Fuel Agent Debates with this MCP Server

This MCP server provides the raw material for high-quality agent conversations. By giving your agents access to real-time CRM data, you move their discussions from theoretical to practical. They can argue about actual leads, existing customers, and real invoices. Setup is quick with the `autogen-ext` package. The `mcp_server_tools` function fetches all seven Clientjoy tools and prepares them for your agents. The `McpToolAdapter` handles the background work, so your agents can focus on using the tools, not on how to call them.

Setup guide

Set up Clientjoy 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 Clientjoy 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="Clientjoy_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

It's when you have multiple agents, each with a role, discussing your Clientjoy data. For instance, a 'sales' agent and a 'finance' agent can debate the pros and cons of a new sales proposal using live data from your CRM.

Yes. You can configure one agent to be a 'Lead Qualifier' using `list_leads` and another to be an 'Account Manager' using `get_customer_details`. They can then collaborate on managing your Clientjoy pipeline.

Based on their instructions and the ongoing conversation, agents decide which tool is best for the task. If another agent asks for a client's payment history, the finance agent knows to use the `list_billing_invoices` tool from the MCP server.

That's the feature, not a bug. Disagreement forces the agents to justify their positions using data from the Clientjoy tools. This debate often leads to a better, more well-reasoned final decision than a single agent could produce alone.

Your data is kept private. All communication with the Clientjoy MCP server is encrypted. The agent conversations, which may contain your customer details or invoice data, happen within your controlled AutoGen environment. Vinkius operates on a zero-trust model and never has access to the content of your data.

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