How to Use the HubSpot MCP in AutoGen

Q: How do I load HubSpot tools into AutoGen?

Use mcpservertools with your Vinkius endpoint. The McpToolAdapter automatically converts the tool definitions into a format your AssistantAgent understands.

Q: Can agents delete records without human input?

They can call removecontact if you give them the tool. You should configure a human-in-the-loop step for destructive actions to prevent accidental data loss.

Give your AutoGen agents the ability to debate, analyze, and update HubSpot CRM records through multi-agent consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot MCP to AutoGen

Create your Vinkius account to connect HubSpot 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 HubSpot with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent CRM operations

`get_deal_details` and `get_contact_details` feed live data into your AutoGen conversations. One agent pulls the pipeline numbers, while another acts as a sales manager to critique the deal velocity. They talk it out, reference the actual API data, and reach a conclusion. This setup prevents single-agent hallucinations. A dedicated validation agent can double-check the output of `list_companies` before any updates are approved, ensuring your CRM stays clean.

Automated updates via HubSpot MCP Server

`create_contact` and `link_crm_objects` let your agents take action after they finish debating. Once the group agrees on a data correction, the execution agent fires the API call to update the record. You configure the permissions. A security agent can require human approval before calling `remove_contact`, while routine object linking happens automatically in the background.

Schema discovery for custom workflows

`get_object_schema` acts as the map for your agents. Before attempting any writes, a planning agent reads the schema to understand required fields and custom property names. It then instructs the execution agent exactly how to format the JSON payload for the MCP tool. This eliminates formatting errors and API rejections when dealing with complex, highly customized CRM setups.

Setup guide

Set up HubSpot 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 HubSpot 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="HubSpot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use mcp_server_tools with your Vinkius endpoint. The McpToolAdapter automatically converts the tool definitions into a format your AssistantAgent understands.

Yes. You pass the tool list to any agent that needs it. They can independently call `search_contacts` or `list_deals` during their deliberation process.

No. Vinkius handles the OAuth tokens. Your agents just use the single endpoint URL provided by the platform.

They can call `remove_contact` if you give them the tool. You should configure a human-in-the-loop step for destructive actions to prevent accidental data loss.

Execution happens within an ephemeral sandbox that immediately terminates after the MCP operation. Your internal user IDs, email addresses, and ownership assignments are never logged or stored persistently.

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