How do I format phone numbers for sending SMS?

Phone numbers must include the country code without the 00 prefix. For example: China uses 86 (e.g., 8615800000000), Brazil uses 55 (e.g., 5511999999999), US uses 1 (e.g., 12025551234). The number should be 5-20 digits total. For Chinese domestic SMS, the message must start with a registered signature like [YourBrand].

What's the difference between send_sms and send_international_sms tools?

The `send_sms` tool uses the standard SMS gateway (smssh.253.com) optimized for Chinese domestic messages and requires pre-registered templates and signatures. The `send_international_sms` tool uses the international gateway (intapi.253.com) for global delivery outside China, which supports SenderId and doesn't require Chinese-style signatures. International SMS permissions must be separately enabled in your account.

How does the MD5 signature authentication work?

The Chuanglan API uses MD5 signature authentication for security. Your password is NEVER sent in the request body. Instead, it's combined with the request parameters and timestamp (nonce), then hashed with MD5 to generate a `sign` header. The server validates this signature to ensure request integrity. The framework handles all signature generation automatically — you only need to provide your account and password.

Chuanglan 253 MCP Server for LangChain 10 tools — connect in under 2 minutes

Name: Chuanglan 253
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Chuanglan 253 through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "chuanglan-253-1": {
            "transport": "streamable_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,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Chuanglan 253, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Chuanglan 253 MCP Server

Connect your Chuanglan 253 SMS gateway to any AI agent and transform your communication workflows through natural conversation. Chuanglan (创蓝) is one of China's largest CPaaS providers, handling billions of SMS messages monthly for verification, notifications, and marketing.

LangChain's ecosystem of 500+ components combines seamlessly with Chuanglan 253 through native MCP adapters. Connect 10 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

What you can do

Send SMS Messages — Deliver text messages to any phone number worldwide with country code support
Verification Codes — Send one-time passwords (OTP) for 1-click login flows and two-factor authentication
Voice Verification — Fallback to automated voice calls when SMS delivery is unreliable
Balance Monitoring — Check your SMS credit balance and quota in real-time before campaigns
Delivery Tracking — Query the status of individual messages or entire batches with message IDs
Template Management — List, create, and manage pre-approved SMS templates for compliance
Account Management — View account settings, permissions, and enabled features

The Chuanglan 253 MCP Server exposes 10 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Chuanglan 253 to LangChain via MCP

Follow these steps to integrate the Chuanglan 253 MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 10 tools from Chuanglan 253 via MCP

Why Use LangChain with the Chuanglan 253 MCP Server

LangChain provides unique advantages when paired with Chuanglan 253 through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Chuanglan 253 MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Chuanglan 253 queries for multi-turn workflows

Chuanglan 253 + LangChain Use Cases

Practical scenarios where LangChain combined with the Chuanglan 253 MCP Server delivers measurable value.

RAG with live data: combine Chuanglan 253 tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Chuanglan 253, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Chuanglan 253 tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Chuanglan 253 tool call, measure latency, and optimize your agent's performance

Chuanglan 253 MCP Tools for LangChain (10)

These 10 tools become available when you connect Chuanglan 253 to LangChain via MCP:

create_template

The template must be approved before it can be used. Template content should include variable placeholders like {1}, {2} for dynamic content. Approval typically takes a few minutes to hours. Create a new SMS template in Chuanglan 253

get_account_info

). Get Chuanglan 253 account information and settings

get_sms_balance

Use this to monitor available messaging capacity before sending campaigns. Check SMS account balance on Chuanglan 253

query_batch_sms_status

This is useful for checking the status of bulk SMS campaigns where multiple messages were sent with the same tracking identifier. Query delivery status for a batch of SMS messages

query_sms_status

Returns whether the message was delivered, is pending, or failed, along with timestamps. Query delivery status of a specific SMS message

query_template_list

Templates are pre-approved message formats that can be used for sending. Each template has an ID, name, content, and approval status. List all SMS templates in your Chuanglan account

send_international_sms

The phone number must include the country code without 00 prefix (e.g., 5511999999999 for Brazil). This endpoint uses the international gateway and requires proper permissions. Send an international SMS message via Chuanglan 253

send_sms

The phone number must include the country code (e.g., 86 for China, 55 for Brazil). For Chinese domestic SMS, the message content must start with a signature in brackets like [YourBrand]. Returns submission status and message ID. Send an SMS message via Chuanglan 253 platform

send_verification_sms

This is commonly used for 1-click login flows, phone number verification, and two-factor authentication. The message format should follow the template registered in your account. Phone number must include country code. Send a verification code SMS (1-click login style)

send_voice_verification

This is an alternative to SMS verification, useful when SMS delivery fails or for enhanced security. The code will be spoken in the call. Send a voice verification call with a code

Example Prompts for Chuanglan 253 in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Chuanglan 253 immediately.

"Send a verification code 837462 to phone number 8615800000000."

"Check my SMS balance and account status."

"What's the delivery status of message ID 162575412960104448?"

Troubleshooting Chuanglan 253 MCP Server with LangChain

Common issues when connecting Chuanglan 253 to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Chuanglan 253 + LangChain FAQ

Common questions about integrating Chuanglan 253 MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.