How to Use the DealHub CPQ MCP in AutoGen

Q: How do I inject DealHub CPQ tools into an AutoGen conversation?

Install autogen-extmcp. You fetch the tools using mcpservertools with your Vinkius URL, then pass that list into the AssistantAgent constructor. The adapter handles the schema conversion.

Let your AutoGen agents debate pricing and manage DealHub CPQ sales workflows autonomously through 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 DealHub CPQ MCP to AutoGen

Create your Vinkius account to connect DealHub CPQ 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 DealHub CPQ with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent DealHub CPQ workflows in AutoGen

Complex deals require multiple perspectives. You build a system where a finance agent and a sales agent debate a proposal. They use `mcp_server_tools` to access the DealHub environment over HTTP. The sales agent wants to close fast and calls `create_quote` to generate the sequence. The finance agent immediately intercepts, running `get_quote_status` to verify vault limits before allowing the process to continue. They negotiate the outcome.

Autonomous opportunity management

You don't need to manually update sales stages anymore. A dedicated CRM agent sits in your chat group and monitors the conversation. It runs `list_opportunities` to find deals matching the current discussion. When the agents reach a consensus on pricing, the CRM agent fires `update_opportunity`. It inspects the internal arrays and applies the specific plan math they agreed upon. The entire group sees the confirmation.

Collaborative CRM syncing and user auditing

Keeping systems aligned usually requires a dedicated ops person. Now you assign that role to a specialized agent. This worker pulls active user arrays using `list_users` to verify who owns which account. Once ownership is confirmed, it triggers `sync_crm`. The agent extracts the churn flags and reports back to the chat. If it finds a conflict, it alerts a human manager to step in and review the structural extraction from `open_quote`.

Setup guide

Set up DealHub CPQ 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 DealHub CPQ 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="DealHub CPQ_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp]. You fetch the tools using mcp_server_tools with your Vinkius URL, then pass that list into the AssistantAgent constructor. The adapter handles the schema conversion.

Yes. You can equip specific agents with the tools while keeping others restricted. A reviewer agent might only have access to get_opportunity, while the executer agent holds the keys to create_opportunity.

It does. You configure the MCP client using StreamableHttpServerParams. This keeps the connection open so long-running tasks like sync_crm don't time out the chat.

The MCP Server exposes the exact JSON schema for every tool. AutoGen translates this into a native function signature, so the LLM knows exactly which variables to pass for the plan math.

You only supply a single endpoint token to Vinkius. The agents never see your actual DealHub API keys, and all deep internal arrays they inspect are destroyed instantly when the ephemeral container spins down.

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