How to Use the Chatwoot MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK send messages in Chatwoot?

Yes. The agent calls sendchatmessage to reply to specific conversation IDs. You control the constraints before it executes the write action.

Q: How does the agent know which customer it is talking to?

The model calls getcontactdetails using the contact ID from the active thread. It pulls their name, email, and custom attributes directly.

Q: Will OpenAI Agents SDK hallucinate Chatwoot agent lists?

No. It runs listsupportagents to pull the exact roster from your account. Hand-offs only happen to real user IDs returned by the API.

Build production customer support agents with OpenAI Agents SDK that read Chatwoot history and reply directly.

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 OpenAI Agents SDK

Create your Vinkius account to connect Chatwoot to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

OpenAI Agents SDK for support

Your agent needs context before it talks to a customer. By calling `get_chat_history` and `get_contact_details`, the model pulls the exact timeline of the current issue. It reads past messages and formulates a response based on your safety constraints. Then it fires back an answer via `send_chat_message` through the MCP connection without leaving the guardrails you configured.

Route tickets across inboxes

Not every conversation belongs to an autonomous system. The code pulls active threads using `list_woot_conversations` and checks which channel they came from via `list_chatwoot_inboxes`. If a user gets angry, your agent hands the task off to a specialized human routing agent. That secondary agent checks `list_support_agents` and assigns the thread to a real person immediately.

Connect this MCP Server safely

Tracing matters when code talks to your users. You pass the Vinkius endpoint into `MCPServerStreamableHttp` and hand it directly to your Agent constructor. Every tool call gets logged in your dashboard for review. Set `cacheToolsList=True` during initialization so the model discovers the Chatwoot endpoints instantly on boot.

Setup guide

Set up Chatwoot MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Chatwoot tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Chatwoot tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Chatwoot tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Chatwoot Agent",
            instructions="You have access to Chatwoot tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the openai-agents package via pip. Initialize MCPServerStreamableHttp with your Vinkius URL and pass it to the mcp_servers array in your setup.

Yes. The agent calls send_chat_message to reply to specific conversation IDs. You control the constraints before it executes the write action.

The model calls get_contact_details using the contact ID from the active thread. It pulls their name, email, and custom attributes directly.

No. It runs list_support_agents to pull the exact roster from your account. Hand-offs only happen to real user IDs returned by the API.

Vinkius runs the connection inside a V8 Isolate Sandbox. Your chat histories and contact emails stay isolated during the session and disappear the moment the task finishes.

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