How to Use the ClickSend MCP in LangChain

Q: How do I connect the ClickSend MCP to LangChain?

Install langchain-mcp-adapters. Point the MultiServerMCPClient to your Vinkius endpoint URL. Call client.gettools() and pass them straight into your agent setup.

Q: Can my LangChain agent read inbound SMS from ClickSend?

Yes. The agent uses the listreceivedsms tool to pull recent messages. You can then feed those replies into a prompt template to generate automated responses.

Q: How does LangChain handle ClickSend account limits?

Have your agent call getclicksendaccountinfo before executing bulk sends. If the balance is too low, the chain can halt and alert you instead of failing mid-run.

Build communication pipelines in LangChain that trigger texts, check account balances, and track physical mail automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickSend MCP to LangChain

Create your Vinkius account to connect ClickSend 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 ClickSend with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire the ClickSend MCP Server into ReAct agents

LangChain thrives on sequential logic, making the `send_clicksend_sms` tool perfect for ReAct agents. You drop the tool into your setup, and the agent figures out exactly when to fire off an alert. If a previous tool in your chain finds a critical server error, the agent grabs the on-call number and sends a text immediately. Phone numbers need E.164 formatting, which LangChain handles easily through an intermediate prompt node. You get full visibility into the execution path via LangSmith, so you know exactly which inputs triggered the message.

Monitor outbound campaigns

Before firing another message, your agent can call `list_sms_marketing_campaigns` to check what already went out. Sometimes you need to know the status of scheduled blasts to avoid spamming your customers. The MCP tool pulls the exact campaign details straight into your chain's memory. It pairs perfectly with `get_sms_outbound_history` and `get_voice_call_history`. The chain reads the logs, parses the delivery statuses, and decides if a follow-up text is necessary.

Read inbound replies dynamically

Two-way messaging works cleanly by scheduling a chain that pings `list_received_sms` every few minutes. The agent pulls fresh customer replies and holds them in persistent context. You never have to manually check the dashboard. Once the agent reads the inbound text, it routes the content through your LLM to determine intent. If it is a support request, the chain logs it in your ticketing system and texts back a confirmation.

Setup guide

Set up ClickSend 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 ClickSend 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({
    "clicksend-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 ClickSend 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 ClickSend. 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 ClickSend 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 ClickSend MCP in LangChain

Install `langchain-mcp-adapters`. Point the `MultiServerMCPClient` to your Vinkius endpoint URL. Call `client.get_tools()` and pass them straight into your agent setup.

Yes. The agent uses the `list_received_sms` tool to pull recent messages. You can then feed those replies into a prompt template to generate automated responses.

Have your agent call `get_clicksend_account_info` before executing bulk sends. If the balance is too low, the chain can halt and alert you instead of failing mid-run.

The API requires E.164 format. Just add a system prompt telling your LangChain agent to format all phone numbers correctly before it calls the send tool.

Vinkius runs the integration inside an ephemeral V8 isolate sandbox. Your phone numbers, inbound text contents, and physical mailing addresses never persist on our infrastructure. The sandbox spins up, executes the API call, and immediately dies.

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