How to Use the HubSpot MCP in CrewAI

Q: How do I restrict which HubSpot tools CrewAI can use?

Use the toolfilter configuration when setting up your server connection. This lets you expose read-only tools to research agents while keeping write access locked down.

Build autonomous CrewAI teams that research, update, and manage your HubSpot pipeline around the clock.

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 CrewAI

Create your Vinkius account to connect HubSpot to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign HubSpot tasks to specialized agents

This MCP Server turns your CRM into a shared workspace for your autonomous crew. You assign a research agent to run `list_companies` and gather intelligence on new accounts. Once the researcher finishes, it passes the context to an action agent. That second agent uses `create_contact` to populate the database. It splits the CRM workload exactly how a human sales floor operates.

Audit and clean your pipeline autonomously

The `search_contacts` tool on this MCP Server lets a moderation agent hunt down outdated entries automatically. Data hygiene usually eats up hours of manual spreadsheet matching. The agent compares records against your internal rules. When it finds a dead lead, it executes `remove_contact` to keep your database lean. It purges stale HubSpot contacts in the background every single night.

Discover schemas for CrewAI MCP Server

The `get_object_schema` tool provides the exact blueprints for your specific account before agents start writing data. Your crew needs to know how custom properties are formatted. A manager agent reads this schema and instructs subordinate agents on how to build their payloads. When they call `link_crm_objects`, the associations work on the first try. The HubSpot association maps perfectly.

Setup guide

Set up HubSpot MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke HubSpot tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="HubSpot Analyst",
    goal="Access and analyze HubSpot data via MCP.",
    backstory="Expert analyst with direct HubSpot access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent HubSpot transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="HubSpot Analyst",
        goal="Access and analyze HubSpot data via MCP.",
        backstory="Expert analyst with direct HubSpot access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HubSpot transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

The simplest way is passing your Vinkius endpoint directly into the `mcps` array when defining the agent. For more control, import `MCPServerHTTP` and use a tool filter.

Yes. Your entire crew shares the connection. A monitoring agent can check `list_deals` while a separate responder agent updates contact records in parallel.

Use the `tool_filter` configuration when setting up your server connection. This lets you expose read-only tools to research agents while keeping write access locked down.

It does. You can designate a manager agent to review the output of `get_deal_details` before deciding which subordinate agent should take the next action.

Your sales rep names and contact lists transit through an isolated Vinkius sandbox that executes the request and immediately terminates. No customer data is ever written to disk or retained after the crew finishes its task.

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