How to Use the SleekFlow MCP in LangChain

Q: What if I need to track my communication data in LangChain?

You can run tools like listconversations, which gives you the full history. This output is then part of your chain's state, allowing subsequent steps or agents to reference that raw conversation data for context.

LangChain: Build multi-step conversational agents that manage customer interactions across channels.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SleekFlow MCP to LangChain

Create your Vinkius account to connect SleekFlow to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SleekFlow with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Sequential Conversation Flow

Your agent decides the exact order of operations. For example, it can first use `get_contact_details` to pull up a user's history, then call `list_conversations` to see if recent messages exist across channels. This output becomes input for the next step in your chain. The agent doesn't just run tools; it reasons about which tool to fire and when—a critical feature for complex customer service logic.

Multi-Channel Tooling

The MCP Server supports multiple endpoints, allowing you to build a single chain that manages diverse channels. You can run tools like `list_channels` and then use the gathered data to guide the agent in sending replies via `send_message` across WhatsApp or Instagram. This eliminates needing separate code paths for each platform. The entire process stays within one cohesive, observable flow.

Contact Management Chains

Need to categorize a user? Start by calling `list_contacts` to get the roster, then use `list_contact_labels` to check existing tags. Finally, the chain can pass that data to an external system or use it to formulate the next action. It's perfect for workflows where classifying a contact is just as important as replying to them. The agent treats labels and contacts equally in its decision-making process.

Setup guide

Set up SleekFlow 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 SleekFlow 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({
    "sleekflow-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 SleekFlow 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 SleekFlow. 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 SleekFlow 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 SleekFlow MCP in LangChain

LangChain lets your agent build a chain that manages conversations across multiple channels. The agent first checks all connected platforms via `list_channels`, then uses the gathered context to formulate and execute replies with `send_message`.

Absolutely. Your agent can use a sequence of tools—like running `list_contacts` followed by `get_contact_details` and then checking labels with `list_contact_labels`—to build a complete picture of the customer.

You can run tools like `list_conversations`, which gives you the full history. This output is then part of your chain's state, allowing subsequent steps or agents to reference that raw conversation data for context.

Yes. Because every tool call outputs structured data, you can pass this information directly into databases or vector stores within your LangChain application. This makes the system highly adaptable.

This server manages customer communication data. Specifically, it handles contact details, conversation logs across WhatsApp and Instagram, and assigned labels.

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