How to Use the Saysimple MCP in LangChain

Q: How do I initialize the Saysimple MCP Server within a LangChain project?

Install langchain-mcp-adapters and use MultiServerMCPClient pointing to your Vinkius endpoint. You then fetch the tools via client.gettools() and pass them directly to your LangChain agent initializer to start managing chats.

Q: Can LangChain agents automatically select WhatsApp templates using Saysimple?

Yes, the agent uses listtemplates to view options, selects the correct one, and passes the formatted JSON to sendmessage. LangChain handles this sequence natively by parsing the tool outputs in its scratchpad.

Q: How does LangChain handle agent-driven contact creation in Saysimple?

Your LangChain agent executes createcontact when it detects a new user, then immediately runs getcontact to confirm the record. This ensures the agent has the correct contact ID before sending any outbound templates.

Q: Can I manage team assignments in Saysimple using a LangChain conversational chain?

You can build a routing chain that calls listchats to find unassigned conversations, then triggers assignchat based on agent availability. This lets LangChain act as an intelligent dispatcher for your support team.

Build multi-step LangChain chains that fetch Saysimple templates and dispatch WhatsApp messages based on live chat routing data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Saysimple MCP to LangChain

Create your Vinkius account to connect Saysimple to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Saysimple with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Saysimple messaging steps directly inside LangChain

The Saysimple MCP Server lets your LangChain agent map out a full customer outreach flow by linking messaging tools together. First, the agent pulls active conversations using `list_chats`, inspects the context, and then decides to route the conversation by calling `assign_chat` to hand it off to a human teammate. If the conversation requires an immediate automated reply instead, LangChain passes that chat ID directly to `get_template` to fetch an approved WhatsApp layout. The chain finishes by executing `send_message` with the correct JSON payload, keeping your entire customer communication loop unified in a single LangGraph execution path.

Trace Saysimple MCP Server calls with LangSmith

Stop guessing why a WhatsApp message failed to send by exposing the Saysimple MCP Server to your LangChain agent. Every interaction with `list_templates` or `get_contact` is automatically traced inside LangSmith with exact latency and token usage metrics. You can inspect the exact JSON payloads passed to `send_message` or verify if `list_channels` returned the correct WhatsApp channel ID. This deep observability ensures your multi-step chains do not run wild or generate invalid API requests when contacting customers.

Route incoming webhooks into active LangChain memory

Keeping customer records updated during a live chat requires immediate access to Saysimple tools. Your LangChain agent calls `list_webhooks` over the MCP connection to identify active event listeners, then updates its internal state using `get_chat` to pull the latest message exchange. When a new user reaches out, the agent runs `create_contact` to log their details before querying `list_contacts` to check for duplicate profiles. This keeps your LangChain memory synchronized with actual customer interactions in Saysimple without manual database syncing.

Setup guide

Set up Saysimple 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 Saysimple 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({
    "saysimple-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 Saysimple 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 Saysimple. 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 Saysimple 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 Saysimple MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` pointing to your Vinkius endpoint. You then fetch the tools via `client.get_tools()` and pass them directly to your LangChain agent initializer to start managing chats.

Yes, the agent uses `list_templates` to view options, selects the correct one, and passes the formatted JSON to `send_message`. LangChain handles this sequence natively by parsing the tool outputs in its scratchpad.

Your LangChain agent executes `create_contact` when it detects a new user, then immediately runs `get_contact` to confirm the record. This ensures the agent has the correct contact ID before sending any outbound templates.

You can build a routing chain that calls `list_chats` to find unassigned conversations, then triggers `assign_chat` based on agent availability. This lets LangChain act as an intelligent dispatcher for your support team.

Vinkius isolates all API calls in a zero-trust sandbox, meaning your Saysimple contact records and chat histories are never stored. The LangChain client communicates directly through an encrypted endpoint token, keeping customer phone numbers and message content completely private.

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