How to Use the Salesquared MCP in LangChain

Q: How does Salesquared work with LangChain memory?

When you pull records with getlead, the agent stores that payload in its session memory. Subsequent steps in the chain can reference that prospect's phone number without making another API call.

Q: What happens if a Salesquared text fails in LangChain?

The sendsms tool returns a failure status to the agent. You write a conditional edge in your graph to handle the error, like sending an email instead or logging the failure.

Q: Are my lead phone numbers safe when using this integration?

We process your sendsms phone numbers in an ephemeral V8 isolate sandbox. The container spins up for the exact millisecond the text sends and self-destructs immediately after. Nothing persists.

Build automated Salesquared communication chains using LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Salesquared MCP to LangChain

Create your Vinkius account to connect Salesquared 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 Salesquared with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Salesquared Leads in LangChain

Your LangChain agent can fire the `create_lead` tool the second a new form drops. You don't have to manually port data across systems. The agent takes the raw payload, structures it, and pushes it directly into your Salesquared account. You can chain this right into a `validate_email` step. If the address bounces, the agent stops the workflow. Passing emails trigger `send_sms` to text the prospect immediately. That cuts your response time from hours to milliseconds.

Trigger Voice Prompts

You use the `create_audio_from_tts` tool to generate custom voice messages on the fly. The MCP Server handles the audio conversion while your agent figures out the script based on previous chain outputs. Once the audio exists, you can drop it into a `create_voice_survey`. You build dynamic outbound calling campaigns without touching a dashboard. LangSmith logs the exact latency of every TTS generation so you know if your pipeline is dragging.

Fetch Live Campaign Data

The `list_campaigns` tool pulls active communication workflows straight into your agent's context window. Your LangChain setup can read exactly what messaging is live and decide which leads belong where. You can drill down further using `get_campaign` to pull specific metrics. If an agent detects low engagement, it can automatically pivot the strategy and execute a `send_voice_otp` instead of a standard text. You build the logic, the tools execute it.

Setup guide

Set up Salesquared 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 Salesquared 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({
    "salesquared-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 Salesquared 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 Salesquared. 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 Salesquared 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 Salesquared MCP in LangChain

You don't pass them to the framework directly. Vinkius handles the auth on the backend. You just point LangChain at the MCP endpoint URL and start building.

Yes. You can configure LangGraph to catch rate limit errors from the MCP Server and retry the tool call. The agent pauses the chain until the window resets.

When you pull records with `get_lead`, the agent stores that payload in its session memory. Subsequent steps in the chain can reference that prospect's phone number without making another API call.

The `send_sms` tool returns a failure status to the agent. You write a conditional edge in your graph to handle the error, like sending an email instead or logging the failure.

We process your `send_sms` phone numbers in an ephemeral V8 isolate sandbox. The container spins up for the exact millisecond the text sends and self-destructs immediately after. Nothing persists.

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