How to Use the Twenty CRM MCP in CrewAI

Q: How can I use CrewAI for complex workflows in Twenty CRM?

You assign roles: one agent collects data (e.g., listcompanies), a second analyzes it, and a third acts on the findings (e.g., calling createopportunity). The agents collaborate using shared memory.

Run autonomous Twenty CRM pipelines with CrewAI's Multi-Agent System.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Twenty CRM MCP to CrewAI

Create your Vinkius account to connect Twenty CRM 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 Twenty CRM with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Operations via MCP Server

CrewAI runs a team of specialized agents, not just one. You can assign Agent A to research and call `list_people`, then give that data to Agent B, which analyzes it for missing information. This simulates an autonomous business process. The whole setup supports shared memory, meaning the output from the first agent is immediately available as context for the next agent in the pipeline.

Orchestrating Twenty CRM Tasks with CrewAI

You build sophisticated pipelines. For instance, one agent finds a key contact using `get_person`, another drafts an internal summary by calling `create_note`, and a third automatically schedules follow-up work by running `create_task`. This happens without human intervention.

Multi-Step CRM Data Management with CrewAI

The framework handles complex sequences. You can set up an escalation workflow: Agent 1 checks for low opportunities using `list_opportunities`; if found, Agent 2 attempts to correct it by calling `update_opportunity`, and finally, a monitor agent takes over to report the status changes.

Setup guide

Set up Twenty CRM 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 Twenty CRM tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You assign roles: one agent collects data (e.g., `list_companies`), a second analyzes it, and a third acts on the findings (e.g., calling `create_opportunity`). The agents collaborate using shared memory.

Yes. You can define a workflow where an agent first reads data with `get_task` and then determines it needs updating, executing the call via `update_task` without prompting.

You can set up a pipeline where an agent iterates through results from `list_notes`, passing the data contextually so that another specialized agent handles bulk actions or summaries.

This MCP Server touches Person, Company, Opportunity, Note, and Task records. The agents can read and write to every single one of these core data types.

It's designed for autonomy. By defining roles and using shared memory, you build monitoring and response systems that run end-to-end without requiring manual intervention.

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