How to Use the Close MCP in AutoGen

Q: How do I hook up Close to AutoGen?

Install autogen-extmcp via pip. Use mcpservertools with the Vinkius URL, then pass the resulting list directly into your AssistantAgent constructor.

Let your AutoGen agents debate and manage your Close sales pipeline through this MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close MCP to AutoGen

Create your Vinkius account to connect Close 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 Close with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen agents debate Close deals

The Close MCP Server gives your AutoGen conversational swarm direct access to your inside sales pipeline. A data-gathering agent pulls the open pipeline using `list_opportunities` and shares the results in the group chat. Then, a risk-assessment agent and a sales-manager agent debate which deals are most likely to close. The framework thrives on competing perspectives. One agent argues for pushing a deal forward based on recent activity, while another flags missing information. They negotiate a consensus before presenting the final pipeline forecast to you.

Qualify prospects through consensus

Setting up an autonomous qualification system starts with raw data. An agent runs `list_leads` to find untouched prospects, then triggers `get_lead_details` for deeper inspection. The swarm reviews the firmographics and communication history. If the agents agree the prospect meets your ideal customer profile, a designated writer agent formats the entry. The system then executes `create_lead` to update the CRM. You build a machine that deliberates before altering your database.

Manage workloads with an MCP Server

Distributing sales actions requires understanding the current state. The swarm uses `get_current_user` to identify the active rep context, followed by `list_crm_tasks` to see the backlog. The agents discuss how to prioritize the pending calls and emails. A performance-focused agent might suggest tackling high-value tasks first, while a compliance agent insists on clearing overdue items. They argue until they reach an agreement on the day's execution plan.

Setup guide

Set up Close 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 Close 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="Close_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp] via pip. Use mcp_server_tools with the Vinkius URL, then pass the resulting list directly into your AssistantAgent constructor.

Yes. You provide the tool list to any agent that needs CRM access. They will decide among themselves who should call get_lead_details during the conversation.

McpToolAdapter automatically converts the server's schema into a format the agents understand. They read the descriptions and pick the right operation based on the chat context.

You build a reviewer agent into the swarm. The reviewer checks the proposed payload for create_lead and argues against it if the data looks wrong, preventing bad entries.

Your task lists and communication logs never leak across sessions. Vinkius handles the auth with a single endpoint token and runs the server in an ephemeral sandbox that dies when the chat ends.

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