How to Use the HubSpot CRM (Full) MCP in CrewAI

Q: Can a CrewAI agent assign deals to specific team members in HubSpot CRM (Full)?

Yes, the agent first calls hslistowners to get the list of active users and their IDs. It then passes the correct owner ID to hscreatedeal or updates the record directly.

Q: How do CrewAI agents collaborate when updating HubSpot CRM (Full) contacts?

One agent can search for a contact using hssearchcontacts and pass the returned ID to a second agent. That second agent then uses hscreatenote or updates the lifecycle stage to keep the record current.

Q: How do I limit which HubSpot CRM (Full) MCP tools a CrewAI agent can access?

You use the MCPServerHTTP class from crewai.mcp and define a toolfilter. This restricts the agent's access, ensuring it only runs tools like hssearchdeals while blocking creation tools.

Q: Can my crew search across both companies and contacts?

Yes, agents can run hssearchcompanies to find organizational context and hssearchcontacts to find individual people. This allows the crew to build a complete picture of an account before updating records.

Deploy specialized agent teams in CrewAI to manage your HubSpot CRM pipelines, contacts, and tickets autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot CRM (Full) MCP to CrewAI

Create your Vinkius account to connect HubSpot CRM (Full) 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 CRM (Full) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent lead enrichment in CrewAI

The `hs_search_contacts` tool scans your CRM for specific names, emails, or phone numbers to locate existing profiles. In a CrewAI setup, an enrichment agent uses this MCP tool to find a contact, while a separate researcher agent gathers background details. Once the research finishes, a CrewAI writer agent uses `hs_create_note` to log the new intelligence directly onto the HubSpot contact's timeline. This division of labor keeps your HubSpot sales data rich without manual data entry.

Automate pipeline monitoring with this MCP Server

The `hs_search_deals` tool returns active opportunities, including their pipeline stages, monetary values, and expected close dates. A monitoring agent in your CrewAI team runs this search daily to identify stagnant deals in the pipeline. If a HubSpot deal requires attention, the CrewAI agent uses `hs_create_note` to flag the account owner or update the deal status. This keeps your pipeline moving without requiring manual oversight.

Route and escalate support tickets autonomously

The `hs_search_tickets` tool searches your support queue by keyword to find open customer issues. A triage agent in CrewAI analyzes these tickets, while an escalation agent uses `hs_create_ticket` to route urgent problems to high-priority queues. The CrewAI team queries `hs_list_owners` to find active support reps and assign the ticket directly in HubSpot. This ensures customer problems reach the right HubSpot owner immediately via CrewAI automation.

Setup guide

Set up HubSpot CRM (Full) 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 CRM (Full) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent HubSpot CRM (Full) 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 CRM (Full) Analyst",
        goal="Access and analyze HubSpot CRM (Full) data via MCP.",
        backstory="Expert analyst with direct HubSpot CRM (Full) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HubSpot CRM (Full) 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 CRM (Full) 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 CRM (Full) MCP in CrewAI

Yes, the agent first calls `hs_list_owners` to get the list of active users and their IDs. It then passes the correct owner ID to `hs_create_deal` or updates the record directly.

One agent can search for a contact using `hs_search_contacts` and pass the returned ID to a second agent. That second agent then uses `hs_create_note` or updates the lifecycle stage to keep the record current.

You use the `MCPServerHTTP` class from `crewai.mcp` and define a `tool_filter`. This restricts the agent's access, ensuring it only runs tools like `hs_search_deals` while blocking creation tools.

Yes, agents can run `hs_search_companies` to find organizational context and `hs_search_contacts` to find individual people. This allows the crew to build a complete picture of an account before updating records.

All MCP tool requests execute inside secure, single-use V8 environments on Vinkius. Your contacts, notes, and deal values are never cached or stored, ensuring your CRM data remains private and compliant with your organizational security policies.

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