How to Use the Chaport MCP in LangChain

Q: How do I connect the Chaport MCP Server to LangChain?

Install langchain-mcp-adapters and define a MultiServerMCPClient pointing to your Vinkius endpoint. Then call client.gettools() and pass the resulting array to your agent constructor.

Q: Can LangChain agents reply to Chaport chats automatically?

Yes. Your chain can evaluate incoming text and trigger the sendagentmessage tool. You control the reasoning pipeline that decides exactly what the agent says.

Connect Chaport to LangChain to build ReAct agents that track visitors and reply to live chats automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chaport MCP to LangChain

Create your Vinkius account to connect Chaport 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 Chaport with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Chaport MCP Server pipelines

Give your ReAct agents direct control over customer support queues. By calling `list_website_visitors`, the agent identifies who is browsing your site right now. It can then pull context using `get_visitor_details` to feed directly into the next step of your chain. You build the reasoning logic while the agent decides when to engage. Once it determines a user needs help based on intermediate chain results, it executes `send_agent_message` to fire off a response in real time.

Trace operator availability in LangSmith

Managing a distributed support team requires knowing who is actually at their keyboard. Your agent can run `list_online_agents` and `list_chaport_operators` to map out team capacity before routing a complex ticket. Every one of these tool calls gets logged in LangSmith. You see exactly how many tokens were spent checking availability and how long the API took to respond.

Chain chat histories into vector stores

Support context often spans multiple sessions. A LangGraph setup can trigger `get_visitor_last_chat` to see what happened yesterday, then immediately run `get_chat_history` for the full timeline. Output from those tools becomes the input for your embedding models. The agent formats the raw chat transcripts and ships them off to a database, giving your future chains instant recall on past customer issues.

Setup guide

Set up Chaport 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 Chaport 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({
    "chaport-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 Chaport 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 Chaport. 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 Chaport 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 Chaport MCP in LangChain

Install `langchain-mcp-adapters` and define a `MultiServerMCPClient` pointing to your Vinkius endpoint. Then call `client.get_tools()` and pass the resulting array to your agent constructor.

Yes. Your chain can evaluate incoming text and trigger the `send_agent_message` tool. You control the reasoning pipeline that decides exactly what the agent says.

Webhooks just dump data. A ReAct agent dynamically decides which tools to call, like checking `get_my_agent_profile` first to ensure it has the right permissions before engaging a visitor.

It tracks every single execution. You get full visibility into the latency and token cost of your Chaport calls right in your tracing dashboard.

Vinkius isolates your server in an ephemeral V8 sandbox. Visitor email addresses, IP details, and raw chat transcripts pulled from Chaport never persist on the host machine after your chain finishes running.

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