How to Use the Chatwoot MCP in CrewAI

Assemble a full customer support team of autonomous agents. Let your CrewAI agents manage Chatwoot conversations from start to finish.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chatwoot MCP to CrewAI

Create your Vinkius account to connect Chatwoot 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 Chatwoot with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build an Autonomous Support Crew

This isn't about a single agent; it's about a team. With CrewAI, you can create a 'Triage Agent' that uses `list_woot_conversations` to find new chats. It then passes them to a 'Research Agent' that uses `get_chat_history` and `get_contact_details` to build context. The Research Agent hands a summary to a 'Drafting Agent' who prepares a reply. Finally, a 'Sending Agent,' with permission to use `send_chat_message`, posts the response. You're building an entire operational process with specialized AI roles.

An MCP Server for Your Autonomous Crew

You can give different agents in your crew access to different Chatwoot tools. Your 'Analyst Agent' might only have read-access tools like `list_chatwoot_contacts` and `get_conversation_details`, preventing it from making changes. Meanwhile, your 'Operator Agent' gets the keys to `send_chat_message`. CrewAI's `tool_filter` option for MCP servers makes this easy to configure. This lets you enforce a clear separation of duties within your autonomous team for safer, more predictable operations.

Continuous Chatwoot Monitoring

Set up a CrewAI process to run 24/7. One agent's entire job can be to constantly poll for new conversations using `list_woot_conversations`. As soon as it finds one, it triggers the rest of the crew to spring into action. This is how you build an autonomous first-level support system. The crew can handle initial responses, collect information from the customer, and even resolve simple issues on its own by coordinating their use of the Chatwoot tools.

Setup guide

Set up Chatwoot 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 Chatwoot tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass the Vinkius MCP URL directly into the `mcps` list when you define your agent. For more control, you can use `MCPServerHTTP` from `crewai.mcp` and specify exactly which tools that particular agent is allowed to use.

Absolutely. That's a perfect use case for CrewAI. You can create a 'Researcher' agent with read-only tools like `get_chat_history` and a 'Responder' agent that is the only one in the crew allowed to use `send_chat_message`.

A common and effective setup is a Triage agent, a Research agent, and a Response agent. The Triage agent finds new work, the Research agent uses Chatwoot tools to gather context, and the Response agent takes action.

Yes, it works with both. You can have agents work on a Chatwoot ticket one after another in a sequence, or have a 'manager' agent delegate tasks like 'look up this contact' to subordinate agents. The tools function the same either way.

Yes. Every request your agent makes to access Chatwoot data, like conversation history or contact details, is executed in a dedicated, single-use sandbox. The server instance exists only for the duration of that request and keeps no logs of the data that passes through.

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