How to Use the Customers.ai MCP in LangChain

Q: Can I trace tool calls with LangSmith?

Every tool execution, including inputs to sendrichmessage and outputs from searchcontacts, shows up in your LangSmith dashboard. You see the exact latency and token usage for every single API call.

Turn anonymous web traffic into qualified leads by chaining Customers.ai tools directly inside your LangChain pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customers.ai MCP to LangChain

Create your Vinkius account to connect Customers.ai 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 Customers.ai with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain anonymous visitor discovery to instant SMS outreach

The `list_xray_leads` tool grabs anonymous website visitors so your LangChain agents can immediately act on them. Then, the agent passes these visitors to `search_contacts` to see if they already exist in your system. If they are new, the chain triggers `send_text_message` to initiate an immediate conversation. You get full observability into this pipeline through LangSmith tracing. Every raw payload, latency jump, and tool transition is logged. This lets you debug exactly why a message failed or how a contact got updated without digging through raw logs.

Dynamic contact tagging and profiling in LangChain agents

`add_tag_to_contact` writes custom labels to your lead database based on how a user interacts with your LangChain agent. Your agent evaluates the user's intent during a live chat, updates their profile with `update_contact_attributes`, and applies tags to segment them for future campaigns. Running this via a managed MCP Server on Vinkius means your code stays clean. You don't have to write custom API wrappers or handle token expiration. The adapter maps the Customers.ai schema directly into your active LangGraph state.

Automated lead enrichment and validation

`get_contact` pulls deep profile details for any identified visitor to help your LangChain agent personalize its responses. To fill in the blanks, the agent checks current attributes, decides if more data is needed, and uses `update_contact_attributes` via the MCP Server. Combining this with your vector databases or internal CRM tools happens in a single run. By configuring the agent to check your database first, you can fall back to the Customers.ai API if the contact details are missing.

Setup guide

Set up Customers.ai 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 Customers.ai 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({
    "customersai-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 Customers.ai 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 Customers.ai. 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 Customers.ai 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 Customers.ai MCP in LangChain

Install the adapters package via pip, then initialize the client with your Vinkius endpoint. You grab the tools with a single call and pass them to your LangGraph agent. Auth is handled at the proxy level, so you only need one token.

Yes, that is the core strength of this setup. Your agent takes the output of `list_xray_leads` and feeds it directly into `get_contact` or `add_tag_to_contact` in a single execution loop.

Your agent manages rate limits through standard backoff strategies built into your runner. Because Vinkius hosts the connection in a sandboxed environment, connection overhead is minimal, leaving you to focus on logic.

Every tool execution, including inputs to `send_rich_message` and outputs from `search_contacts`, shows up in your LangSmith dashboard. You see the exact latency and token usage for every single API call.

All visitor profiles and phone numbers are processed inside ephemeral V8 isolates on Vinkius. Your API keys never touch the client side, and no customer data is cached on our servers after the request completes.

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