How to Use the Chatwoot MCP in Pydantic AI

Q: How do I connect Chatwoot to Pydantic AI?

Run pip install pydantic-ai-slimmcp. Pass your Vinkius URL into MCPToolset and assign it to your agent configuration.

Q: Can Pydantic AI send Chatwoot messages?

The framework exposes sendchatmessage directly to your chosen model. It validates the conversation ID and message string before execution.

Q: How do I find specific users in my account?

Your agent executes listchatwootcontacts to pull the directory. It parses the resulting JSON into strict Python objects for safe handling.

Q: Does Pydantic AI work with Chatwoot custom inboxes?

Yes. It runs listchatwootinboxes to map out your WhatsApp, SMS, and web widget channels. The model routes replies to the correct origin automatically.

Build type-safe customer service agents that validate every Chatwoot payload at runtime using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Chatwoot to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stop hallucinating support data

Broken JSON crashes production systems. When your agent calls `get_conversation_details`, the framework validates the incoming payload against your defined schemas immediately. If the API returns a missing contact ID, the system throws a loud validation error. You catch the failure in your code instead of sending garbage text to a customer.

Pydantic AI meets Chatwoot

You are not locked into a specific LLM provider. Teams use Claude for complex triage via `get_chat_history` and switch to a cheaper local model for basic routing. The tools remain exactly the same regardless of the brain you attach. The agent pulls the roster with `list_support_agents` and assigns tickets predictably every time.

Connect this MCP Server easily

The old HTTP server classes are gone. You just install the slim package with MCP extras and point `MCPToolset` at your Vinkius endpoint. Pass that single object into the toolsets array of your Agent. It auto-discovers endpoints like `list_chatwoot_inboxes` and builds the necessary JSON schemas under the hood.

Setup guide

Set up Chatwoot MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "chatwoot-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Chatwoot tools.",
)

result = await agent.run("List recent Chatwoot transactions")
print(result.output)

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 Pydantic AI

Run pip install pydantic-ai-slim[mcp]. Pass your Vinkius URL into MCPToolset and assign it to your agent configuration.

The framework exposes send_chat_message directly to your chosen model. It validates the conversation ID and message string before execution.

Your agent executes list_chatwoot_contacts to pull the directory. It parses the resulting JSON into strict Python objects for safe handling.

Yes. It runs list_chatwoot_inboxes to map out your WhatsApp, SMS, and web widget channels. The model routes replies to the correct origin automatically.

We isolate the connection in a stateless V8 sandbox. Phone numbers, emails, and chat logs pass through memory only and vanish completely when the run ends.

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