How to Use the 360dialog MCP in LlamaIndex

Q: How does LlamaIndex index the output from 360dialog tools?

When you use the McpToolSpec, LlamaIndex wraps each tool call. The JSON or text response from the 360dialog API is automatically parsed and embedded into your configured vector store. This makes your API activity searchable.

Q: Can I ask my LlamaIndex agent questions about my 360dialog templates?

Yes. First, have your agent run the listtemplates tool. Once that data is indexed, you can ask natural language questions like 'show me all templates for password resets' and LlamaIndex will query the vectorized API responses.

Q: Is it possible to search contacts I've checked with 360dialog and LlamaIndex?

Definitely. After your agent uses the checkcontacts tool, the results—including valid and invalid numbers—are indexed. You can then query your agent to find which contacts were successfully validated on a certain day.

Build LlamaIndex RAG apps that index 360dialog API data, letting you query your WhatsApp templates and contacts with natural language.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 360dialog MCP to LlamaIndex

Create your Vinkius account to connect 360dialog 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 360dialog with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn API Data into a Knowledge Base

This server exposes tools for interacting with the 360dialog API. Your LlamaIndex agent can `list_templates` to see all available message formats or `check_contacts` to validate a list of phone numbers. It's direct access to your WhatsApp account data. LlamaIndex doesn't just call these tools; it indexes their output. After your agent runs `list_templates`, the results are added to a vector store. Now you can ask 'which templates mention shipping confirmation?' and get an answer grounded in the actual API response.

Send Messages Based on Indexed Data

Your agent can use its knowledge base to act. After finding the right template from its index, it can execute the `send_template_message` tool. The agent can also `send_message` for simple texts or `send_media_message` for files. This creates a powerful RAG pipeline. A query about a user's status could hit your internal documents, find their phone number, use the `check_contacts` tool to validate it, find the right 'status_update' template from the index, and finally `send_template_message`—all in one flow.

Build Your LlamaIndex Agent Faster

This MCP Server handles the boilerplate of talking to the 360dialog API. You don't need to write custom API clients or parsers. Just use the `McpToolSpec` to load the tools directly into your LlamaIndex agent. The tools like `get_media` and `upload_media` are ready to go. Your agent can build a workflow to get a file, upload it, and send it, with LlamaIndex automatically indexing the metadata from each step for future queries.

Setup guide

Set up 360dialog 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 360dialog 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 360dialog tools.",
)
response = await agent.run("List recent 360dialog 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 360dialog. 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 360dialog 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 360dialog MCP in LlamaIndex

When you use the `McpToolSpec`, LlamaIndex wraps each tool call. The JSON or text response from the 360dialog API is automatically parsed and embedded into your configured vector store. This makes your API activity searchable.

Yes. First, have your agent run the `list_templates` tool. Once that data is indexed, you can ask natural language questions like 'show me all templates for password resets' and LlamaIndex will query the vectorized API responses.

Definitely. After your agent uses the `check_contacts` tool, the results—including valid and invalid numbers—are indexed. You can then query your agent to find which contacts were successfully validated on a certain day.

This server saves you from writing and maintaining a custom API connector. The tools are pre-defined, authenticated, and ready to be loaded with `McpToolSpec`. It gets you from zero to a working RAG agent much faster.

The MCP Server itself stores nothing. LlamaIndex, however, will index the *output* of the tools you call. This means data like template names, contact statuses, and media metadata will be stored in *your* vector database, under your control.

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