How to Use the Wati MCP in LlamaIndex

Q: How can I use Wati's MCP Server output with LlamaIndex?

You expose tools like listmessages using the BasicMCPClient. The key is passing the tool results to the FunctionAgent, which then indexes that data into a searchable knowledge base for RAG.

Q: What if I want to check Wati status when querying with LlamaIndex?

You index the output of checkwatistatus. This lets your system answer questions like, 'Was Wati connected at 2 PM yesterday?' by searching the historical records.

Q: Can I update data and make it searchable for LlamaIndex?

Yes. Although updatecontact changes external state, you can run a follow-up tool call that retrieves the new contact details, index those results, and make them part of your queryable knowledge base.

Q: What data types does Wati's MCP Server expose for LlamaIndex?

The server exposes structured messaging content from listmessages, specific contact attributes from getcontact, and the list of available tags via listtags.

Index and search messaging data with LlamaIndex and Wati.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wati MCP to LlamaIndex

Create your Vinkius account to connect Wati 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 Wati with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Past Communication Records

The `list_messages` tool output becomes a searchable knowledge chunk. You can index past conversation transcripts, allowing your RAG application to answer questions like 'What did we discuss last week?' based on actual API data. This is huge for grounding answers in reality. Instead of guessing, the agent queries the indexed message history and pulls back specific context from `list_messages`.

Build Indexed Contact Profiles

When you run `get_contact`, LlamaIndex indexes the resulting contact details into your vector store. This means subsequent queries can search not just by name, but by any attribute stored in the profile. Developers build rich knowledge bases this way. The system uses the indexed attributes from calls like `list_contacts` to provide highly specific answers about users.

Retrieve and Query Templates

You can index template definitions by calling `list_templates`. This allows your knowledge graph to understand what kinds of messages are possible, even if the message hasn't been sent yet. The query process works like this: a user asks 'How do I talk about X?', and the system searches the indexed results from `get_template` to pull back relevant structure and details.

Setup guide

Set up Wati 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 Wati 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 Wati tools.",
)
response = await agent.run("List recent Wati 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 Wati. 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 Wati 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 Wati MCP in LlamaIndex

You expose tools like `list_messages` using the BasicMCPClient. The key is passing the tool results to the FunctionAgent, which then indexes that data into a searchable knowledge base for RAG.

You index the output of `check_wati_status`. This lets your system answer questions like, 'Was Wati connected at 2 PM yesterday?' by searching the historical records.

Yes. Although `update_contact` changes external state, you can run a follow-up tool call that retrieves the *new* contact details, index those results, and make them part of your queryable knowledge base.

The server exposes structured messaging content from `list_messages`, specific contact attributes from `get_contact`, and the list of available tags via `list_tags`.

The server touches sensitive communication records. You must ensure that any indexed message content from `list_messages` adheres to strict internal compliance and PII handling rules.

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