How to Use the Cloze MCP in CrewAI

Q: How do I connect the Cloze MCP Server to my CrewAI agents?

You just pass the Vinkius endpoint URL directly into the mcps parameter when initializing your agent. If you want more control, import MCPServerHTTP from the CrewAI library to filter specific tools like getperson for specific agents.

Q: Can a CrewAI agent update custom fields inside Cloze?

Yes, your agents can run listcustomfields to find the exact keys used in your workspace. Once they know the structure, they can pass those custom values when running createperson or updateperson.

Give your CrewAI agents direct, autonomous access to Cloze CRM data to manage contacts and track deals without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloze MCP to CrewAI

Create your Vinkius account to connect Cloze 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 Cloze with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous CRM Updates for CrewAI Agents

The `create_person` tool allows your agents to instantly build new contact profiles when researching leads. You don't have to copy and paste email addresses anymore. Your agents run `update_person` to keep existing records fresh whenever they uncover new phone numbers or social links during their runs. This MCP Server setup means your team of agents handles the boring data entry. They can query existing contacts using `get_person` to check for history before making any changes, keeping your database clean without manual oversight.

Smart Deal and Project Tracking

The `create_project` tool lets your agents spin up new deals, properties, or projects in Cloze automatically. When a deal progresses, a monitor agent can pull active deals with `list_projects` to evaluate progress and assign follow-up tasks to other agents. Instead of waiting for a human to update project stages, the agents handle it. They use `list_companies` to map contacts to their organizations, ensuring every new deal links to the right corporate entity.

Targeted Outreach and Tag-Based Segmentation

The `search_people_by_tag` tool gives your agents the power to segment lists of qualified leads instantly. This lets your marketing agents pull highly specific lists, read custom properties using `list_custom_fields`, and draft highly personalized messaging. Your CrewAI agents use this deep context to decide who gets emailed next. They query `list_people` to filter out inactive leads, ensuring your outreach campaigns only target active, high-value prospects.

Setup guide

Set up Cloze 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 Cloze tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Cloze 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 Cloze. 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 Cloze 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 Cloze MCP in CrewAI

You just pass the Vinkius endpoint URL directly into the `mcps` parameter when initializing your agent. If you want more control, import `MCPServerHTTP` from the CrewAI library to filter specific tools like `get_person` for specific agents.

Yes, your agents can run `list_custom_fields` to find the exact keys used in your workspace. Once they know the structure, they can pass those custom values when running `create_person` or `update_person`.

The CrewAI framework manages tool execution sequentially or hierarchically depending on your crew's design. If multiple agents need to check `list_projects` or `list_people` at the same time, Vinkius handles the traffic safely.

The server uses the email address as a matching key when executing `update_person` to prevent duplicates. Your agent should run `get_person` first to see if the contact exists before trying to create a new record.

Absolutely. Vinkius runs this MCP server inside an isolated V8 sandbox, meaning your API tokens and contact details are never exposed. Your sensitive client lists and project records stay encrypted and ephemeral, processed only during the active agent execution loop.

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