How to Use the Kontak MCP in LangChain

Q: How do I connect Kontak to LangChain?

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient pointing to your Vinkius endpoint. This registers all ten Kontak MCP tools directly into your LangChain agent's runtime, letting it trigger actions immediately.

Q: Can LangChain trace Kontak API failures?

Yes, track every call to getmessagedetails or listkontakmessages using LangSmith. It captures the exact latency, token usage, and payload details for every SMS transaction your agent executes.

Q: How does Kontak handle templates in LangChain?

Your LangChain agent calls listkontaktemplates to fetch your pre-approved layouts, then uses them to format messages. This keeps your automated texts compliant and consistent without hardcoding copy into your Python chains.

Run multi-step messaging chains in LangChain using Kontak to send texts and audit logs based on real-time conversation 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 LangChain

Create your Vinkius account to connect Kontak to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step messaging chains with LangChain

Here's the thing: your LangChain agent uses `send_outbound_sms` to dispatch text messages while tracking execution status through LangSmith. If a message fails, the agent immediately triggers `get_kontak_audit_logs` to diagnose the issue, converting raw API errors into logical next steps for the next chain link. This setup lets you build complex routing logic where LangChain evaluates the output of `list_kontak_templates` before choosing the exact text format to send. You get full observability over the entire execution path, from the initial prompt to the final message delivery.

Ground LangChain agent decisions in live contact metadata

The `list_kontak_contacts` tool feeds raw customer records directly into your LangChain ReAct agent so it always has the correct recipient details. Don't hardcode phone numbers. Your agent searches your contact list, pulls specific records with `get_contact_details`, and determines the right communication channel. Combine this with `list_kontak_tags` to ensure your agent only targets customers with specific tags, keeping your messaging campaigns accurate. By feeding these outputs directly into the next chain link, LangChain handles contact segmentation automatically.

Build self-healing webhooks using this MCP Server

This MCP Server exposes `list_kontak_webhooks` to let your LangChain agent inspect and manage your active message triggers. When a webhook fails or drops off, the agent detects the gap during its execution loop and alerts your team with the exact configuration details. Run `get_kontak_account_info` within the same LangChain run to verify your rate limits before blasting out high-volume notifications. This prevents your chains from hitting API bottlenecks and keeps your automated workflows running without manual intervention.

Setup guide

Set up Kontak MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kontak tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kontak-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kontak transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` pointing to your Vinkius endpoint. This registers all ten Kontak MCP tools directly into your LangChain agent's runtime, letting it trigger actions immediately.

Yes, track every call to `get_message_details` or `list_kontak_messages` using LangSmith. It captures the exact latency, token usage, and payload details for every SMS transaction your agent executes.

Your LangChain agent calls `list_kontak_templates` to fetch your pre-approved layouts, then uses them to format messages. This keeps your automated texts compliant and consistent without hardcoding copy into your Python chains.

Configure separate sessions in your LangChain client, each pointing to a different Vinkius token. This lets your agent query `get_kontak_account_info` across different accounts to verify balances before sending messages.

Your SMS content, contact details, and audit logs are protected by Vinkius's isolated V8 sandboxes. This zero-trust MCP Server ensures LangChain only accesses your messaging data during live tool executions, meaning no logs or contact records are stored permanently on Vinkius 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