How to Use the 1msg.io MCP in LlamaIndex

Q: How can I index my WhatsApp history from 1msg.io with LlamaIndex?

You'll set up a routine that calls the listmessages tool from the 1msg.io server. Then, you feed the output into your LlamaIndex ingestion pipeline. This will convert the message history into embeddings and store them in your chosen vector database.

Q: What's the setup for using 1msg.io tools in a LlamaIndex app?

Install the llama-index-tools-mcp package and point the BasicMCPClient at your Vinkius URL. Then, you wrap it with McpToolSpec and call totoollistasync() to get a list of tools for your agent.

Q: Can I use LlamaIndex to search templates in my 1msg.io account?

Absolutely. You can periodically run the listtemplates tool and index the results. This lets your agent perform a semantic search to find the most relevant template for a task, instead of just matching keywords.

Turn your WhatsApp history into a searchable knowledge base with LlamaIndex. Query past 1msg.io conversations and live channel data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 1msg.io MCP to LlamaIndex

Create your Vinkius account to connect 1msg.io 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 1msg.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your WhatsApp History

Use the `list_messages` tool to fetch your WhatsApp chat logs. Then, let LlamaIndex do its thing: embed and index the conversations into a vector store. Now your RAG application has a memory of every customer interaction. You can ask questions in natural language, like "what was the last thing we discussed with the client at +14155552671?" and get answers based on actual message content, not just a database record. It grounds your agent in real-world communication.

Augment RAG with Live Data

Your LlamaIndex agent can query this MCP server for real-time information. Before answering a question, it can call `get_status` to make sure your WhatsApp channel is online or use `list_templates` to see which message formats are currently approved. This fresh data gets injected directly into the prompt. It prevents your agent from giving stale answers and ensures its responses are based on the current state of your 1msg.io account, not just what's in the vector index.

From Query to Action

LlamaIndex isn't just for answering questions. After querying the indexed message history, your agent can take action. It might find that a customer hasn't received a shipping update, then decide to use the `send_message` or `send_template` tool to send one. This closes the loop between insight and execution. The agent finds a problem by querying its knowledge base of past conversations, then uses another tool from the same MCP server to solve it. It's a full cycle.

Setup guide

Set up 1msg.io 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 1msg.io 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 1msg.io tools.",
)
response = await agent.run("List recent 1msg.io 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 1msg.io. 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 1msg.io 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 1msg.io MCP in LlamaIndex

You'll set up a routine that calls the `list_messages` tool from the 1msg.io server. Then, you feed the output into your LlamaIndex ingestion pipeline. This will convert the message history into embeddings and store them in your chosen vector database.

Yes. You can configure your LlamaIndex agent to use tools like `get_status` or `list_templates`. When the agent needs fresh data to answer a query, it will call the tool directly, giving it real-time context.

Install the `llama-index-tools-mcp` package and point the `BasicMCPClient` at your Vinkius URL. Then, you wrap it with `McpToolSpec` and call `to_tool_list_async()` to get a list of tools for your agent.

Absolutely. You can periodically run the `list_templates` tool and index the results. This lets your agent perform a semantic search to find the most relevant template for a task, instead of just matching keywords.

Vinkius isolates every tool call in a zero-trust environment. The 1msg.io server only sees the data for that one operation—like a phone number and message text—and does not store it. Once the API call is complete, the data is gone.

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