How to Use the Infobip (Omnichannel Communications) MCP in LangChain

Q: Can LangChain agents route messages dynamically using Infobip (Omnichannel Communications)?

Yes, your agent calls getpersondetails to check preferred channels, then decides to run either dispatchwhatsappmessage or dispatchsmsmessage based on user preferences.

Q: How does the Infobip (Omnichannel Communications) MCP Server handle retries in LangChain?

The agent checks delivery logs using getdeliveryreports and triggers a fallback chain if a message fails. This ensures high-priority alerts always reach the client.

Q: Can I manage CRM audiences dynamically?

You can query audiences using listcrmpeople and update them using upsertcrmperson inside any standard LangChain runnable. This allows real-time audience segment updates during conversations.

Build multi-step communication chains that route alerts across SMS, WhatsApp, and Email using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Infobip (Omnichannel Communications) MCP to LangChain

Create your Vinkius account to connect Infobip (Omnichannel Communications) 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 Infobip (Omnichannel Communications) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic routing across messaging channels

`dispatch_sms_message` acts as the primary failover when your agent detects a WhatsApp delivery failure. Your LangChain agent evaluates customer profiles using `get_person_details` to determine whether to trigger WhatsApp or SMS first. If the initial route fails, the agent reads the state and immediately calls `dispatch_whatsapp_message` or `dispatch_html_email`. This logic runs inside your chain without hardcoded routing rules, relying on real-time feedback from the Infobip API.

LangChain profile sync via MCP Server

`upsert_crm_person` updates your customer records inside the People CDP directly from agent execution runs. LangChain chains parse raw customer support transcripts, extract contact information, and modify names using `update_person_name`. When customers request data removal, the chain invokes `delete_crm_person` to handle GDPR requirements. This automates database maintenance without manual data entry or separate integration scripts.

Closed-loop message verification via LangSmith

`get_delivery_reports` pulls real-time delivery metrics into your LangChain tracing pipeline. You see the exact latency and delivery status of every message alongside your LLM run logs. By analyzing logs with `list_sms_logs`, your agent can automatically flag failed routes and retry them. This MCP Server integration gives you full observability over your messaging spend and delivery rates.

Setup guide

Set up Infobip (Omnichannel Communications) 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 Infobip (Omnichannel Communications) 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({
    "infobip-omnichannel-communications-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 Infobip (Omnichannel Communications) 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 Infobip. 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 Infobip (Omnichannel Communications) 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 Infobip (Omnichannel Communications) MCP in LangChain

Install langchain-mcp-adapters and instantiate the MultiServerMCPClient with your Vinkius endpoint. Pass the tools retrieved from the server directly to your ReAct agent initialization.

Yes, your agent calls get_person_details to check preferred channels, then decides to run either dispatch_whatsapp_message or dispatch_sms_message based on user preferences.

The agent checks delivery logs using get_delivery_reports and triggers a fallback chain if a message fails. This ensures high-priority alerts always reach the client.

You can query audiences using list_crm_people and update them using upsert_crm_person inside any standard LangChain runnable. This allows real-time audience segment updates during conversations.

All PII, including phone numbers and email addresses processed by upsert_crm_person, goes through a secure V8 isolate sandbox. No customer data is stored on Vinkius servers, maintaining your GDPR compliance.

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