How to Use the Chatwoot MCP in LlamaIndex

Q: How do I load Chatwoot data into LlamaIndex using MCP?

Install llama-index-tools-mcp and initialize the client pointing to your Vinkius server URL. Use McpToolSpec to register tools like listwootconversations as native LlamaIndex tools.

Q: Does LlamaIndex support filtering Chatwoot contacts?

It does. By calling listchatwootcontacts, your LlamaIndex agent retrieves user metadata and applies metadata filters to narrow down its vector index searches.

Q: How do I trigger message sends from a LlamaIndex agent?

Pass the tool list to your FunctionAgent constructor. When the agent resolves a query, it executes sendchatmessage to post the answer back to the customer's inbox.

Index your live Chatwoot support threads via this MCP Server into LlamaIndex vector stores for grounded RAG.

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 LlamaIndex

Create your Vinkius account to connect Chatwoot to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Chatwoot MCP Server data for vector search

The `list_woot_conversations` tool acts as a live data loader for your LlamaIndex document pipeline. It extracts raw support interactions so your LlamaIndex system can convert them into vector embeddings. By indexing these Chatwoot threads, your LlamaIndex RAG system answers customer queries using actual historical resolutions. No more guessing; the LlamaIndex agent finds the exact Chatwoot thread where a teammate solved a similar bug.

Ground agent responses in historical support transcripts

The `get_chat_history` tool pulls the full transcript of any active ticket directly into the LlamaIndex query context. Your LlamaIndex agent reads the historical context to draft replies that align with previous agent notes. To ensure accuracy, the LlamaIndex framework runs semantic checks against your local vector store before invoking `send_chat_message`. This prevents the LlamaIndex agent from hallucinating instructions that contradict your official Chatwoot documentation.

Map customer profiles to query indexes

The `get_contact_details` tool retrieves customer metadata, including custom attributes, to filter your LlamaIndex vector queries. Your LlamaIndex agent customizes its search space based on the customer's specific subscription tier or software version. Combining this with `list_chatwoot_contacts` allows you to build dynamic customer directories in LlamaIndex. The LlamaIndex agent cross-references active Chatwoot issues with contact profiles to spot systemic platform bugs.

Setup guide

Set up Chatwoot MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Chatwoot MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Chatwoot tools.",
)
response = await agent.run("List recent Chatwoot data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the client pointing to your Vinkius server URL. Use `McpToolSpec` to register tools like `list_woot_conversations` as native LlamaIndex tools.

Yes, you can. The engine decomposes complex user queries and calls `get_chat_history` to gather facts before synthesizing the final reply.

It does. By calling `list_chatwoot_contacts`, your LlamaIndex agent retrieves user metadata and applies metadata filters to narrow down its vector index searches.

Pass the tool list to your `FunctionAgent` constructor. When the agent resolves a query, it executes `send_chat_message` to post the answer back to the customer's inbox.

Your customer contact profiles and inbox configurations remain encrypted in transit via HTTPS. Vinkius executes this MCP Server within an ephemeral, zero-trust container, ensuring that no raw support transcripts are stored on intermediate servers.

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