Can I reply to a WhatsApp message through the agent?

Yes! Use the `send_chat_message` tool with the conversation ID. As long as your WhatsApp inbox is connected to Chatwoot, the agent will deliver your reply.

How do I see the full history of a chat?

Use the `get_chat_history` tool with the unique conversation ID. Your agent will fetch all previous messages, allowing you to review the entire interaction.

Where do I find my Chatwoot Access Token?

Log in to Chatwoot, click on your profile avatar in the bottom left, and select 'Profile Settings'. Scroll to the bottom to find your personal 'Access Token'.

Chatwoot MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Chatwoot
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Chatwoot through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Chatwoot "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Chatwoot?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Chatwoot MCP Server

Connect your Chatwoot account to any AI agent and take full control of your customer support and engagement through natural conversation. Streamline how you manage chats across Web, WhatsApp, Facebook, and more.

Pydantic AI validates every Chatwoot tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Conversation Oversight — List and retrieve details for all active and resolved conversations natively
Live Replying — Send messages to customers in active chat sessions flawlessly
Contact Management — List and retrieve detailed customer contact information and history securely
Inbox Intelligence — Monitor all configured inboxes, including Web widgets and social integrations flawlessly
Agent Tracking — List all support agents and manage team availability in real-time
Message History — Access complete chat histories to understand customer context directly within your workspace

The Chatwoot MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Chatwoot to Pydantic AI via MCP

Follow these steps to integrate the Chatwoot MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Chatwoot with type-safe schemas

Why Use Pydantic AI with the Chatwoot MCP Server

Pydantic AI provides unique advantages when paired with Chatwoot through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Chatwoot integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Chatwoot connection logic from agent behavior for testable, maintainable code

Chatwoot + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Chatwoot MCP Server delivers measurable value.

Type-safe data pipelines: query Chatwoot with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Chatwoot tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Chatwoot and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Chatwoot responses and write comprehensive agent tests

Chatwoot MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Chatwoot to Pydantic AI via MCP:

get_chat_history

Retrieve the message history for a specific conversation

get_contact_details

Get detailed information for a specific customer contact

get_conversation_details

Get detailed information for a specific conversation

list_chatwoot_contacts

List all customer contacts

list_chatwoot_inboxes

List all configured inboxes (Web, WhatsApp, etc)

list_support_agents

List all support agents in the account

list_woot_conversations

List all conversations in the account

send_chat_message

Send a message to a customer in a specific conversation

Example Prompts for Chatwoot in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Chatwoot immediately.

"List all active conversations in Chatwoot."

"What did the customer in conversation ID 555 say last?"

"Reply to conversation 555: 'I'll look into this right now for you, Sarah.'"

Troubleshooting Chatwoot MCP Server with Pydantic AI

Common issues when connecting Chatwoot to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Chatwoot + Pydantic AI FAQ

Common questions about integrating Chatwoot MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Chatwoot MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.