How to Use the Kontak MCP in LlamaIndex

Q: How do I load Kontak contacts into LlamaIndex?

Use llama-index-tools-mcp to initialize the client and convert the listkontakcontacts tool into a query engine resource. This lets LlamaIndex index your contact profiles directly into your vector database.

Q: Can LlamaIndex search through old Kontak messages?

Yes, by passing listkontakmessages to your MCP client, LlamaIndex indexes your messaging history. Your agent then performs semantic search over those past SMS conversations to answer user questions.

Q: How does Kontak handle tag filtering in LlamaIndex?

Your LlamaIndex agent queries listkontaktags to understand your contact categories before running a search. It uses these tags as metadata filters in your vector store to restrict search results to specific customer groups.

Q: Can I use Kontak templates for LlamaIndex RAG generation?

Yes, pull your pre-defined message formats using listkontaktemplates to guide how LlamaIndex structures its final outputs. This ensures that the generated answers match your established brand guidelines.

Index live Kontak message histories into LlamaIndex vector stores to ground your RAG applications in real-time SMS data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to LlamaIndex

Create your Vinkius account to connect Kontak 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 Kontak with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live messaging data with this MCP Server

This MCP Server connects `list_kontak_messages` directly to your LlamaIndex pipeline to pull and index your entire SMS history. LlamaIndex takes the raw text payloads, converts them into vector embeddings, and stores them so your agent queries past conversations. By grounding your search in actual message logs, your agent avoids making up facts about previous customer interactions. When a user asks about a past text, LlamaIndex queries the vector index and uses `get_message_details` to pull the exact message for context.

Query Kontak contact directories semantically in LlamaIndex

The `list_kontak_contacts` tool lets LlamaIndex ingest your customer directory and build a searchable knowledge graph of your relationships. Your agent queries this graph to find people based on their notes, tags, or history, rather than relying on exact database matches. Combine this with `get_contact_details` to let your LlamaIndex agent pull rich metadata on demand. It reads the contact's current status and uses that context to ground its responses during search queries.

Audit LlamaIndex agent decisions using system logs

The `get_kontak_audit_logs` tool gives your LlamaIndex indexer direct access to system events for compliance tracking. Index these logs alongside your standard data sources to build an audit trail of every automated action your agent takes. If an agent sends an incorrect text, query your LlamaIndex vector store to find the exact sequence of events. It matches the vector representation of the query against `list_kontak_webhooks` configurations to pinpoint where the logic failed.

Setup guide

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

Use `llama-index-tools-mcp` to initialize the client and convert the `list_kontak_contacts` tool into a query engine resource. This lets LlamaIndex index your contact profiles directly into your vector database.

Yes, by passing `list_kontak_messages` to your MCP client, LlamaIndex indexes your messaging history. Your agent then performs semantic search over those past SMS conversations to answer user questions.

Your LlamaIndex agent queries `list_kontak_tags` to understand your contact categories before running a search. It uses these tags as metadata filters in your vector store to restrict search results to specific customer groups.

Yes, pull your pre-defined message formats using `list_kontak_templates` to guide how LlamaIndex structures its final outputs. This ensures that the generated answers match your established brand guidelines.

Your contact details and SMS records remain secure because Vinkius runs the integration in ephemeral sandboxes. LlamaIndex only pulls data like `get_contact_details` during active queries, and your API keys never leave the secure Vinkius MCP environment.

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