How to Use the Sobot MCP in LangChain

Q: If I need to check multiple support agents' availability with Sobot and LangChain?

You can list all available agents using listagents and then iterate through that list, calling getagentstatus for each one in a controlled sequence. This gives you an aggregate view of team readiness.

Build Multi-Step Reasoning Pipelines with Sobot using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sobot MCP to LangChain

Create your Vinkius account to connect Sobot 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 Sobot with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chaining MCP Tools for Complex Workflows

You write agents that decide which tool to run and in what sequence. For instance, an agent can first call `list_tickets` to pull a list of open issues, then use the ticket IDs found to call `get_ticket_details`, finally using all that data to generate a summary via `get_org_summary`. This capability lets you build full reasoning pipelines. The output from one tool becomes the necessary input for the next step in your chain, making multi-step tasks predictable and verifiable.

Interacting with Sobot's Agent Status

Need to know if a human agent is available before creating a ticket? You can first call `get_agent_status` to check real-time availability. If the status indicates low staff, your chain can then automatically route the request to an internal queue using `create_ticket`, skipping immediate customer interaction. This pattern of checking status and branching logic is key for complex agent routing systems. It prevents wasting resources on tickets that need manual review before they even hit the queue.

Analyzing User Data in Chains

The chain can pull user information from `list_users` to identify account type and subscription tier. This data is critical context when calling `create_ticket`, allowing you to pre-populate priority fields or assign the ticket to a specialized department automatically. By using multiple pieces of customer data together, your agent acts less like a simple API call wrapper and more like an experienced support professional making informed decisions.

Setup guide

Set up Sobot 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 Sobot 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({
    "sobot-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 Sobot 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 Sobot. 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 Sobot 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 Sobot MCP in LangChain

You define the chain's logic. The agent decides which tool to call next based on intermediate results, forming a multi-step reasoning process. You don't write linear code; you build decision graphs.

Sobot handles the raw customer ticket data and knowledge base details. Since LangChain provides full observability via tracing, you can track exactly which data points were accessed during a chain execution.

Yes, the framework supports detailed tracing of every tool call. You get visibility into both token usage and the exact time taken for each step in the overall process.

You can list all available agents using `list_agents` and then iterate through that list, calling `get_agent_status` for each one in a controlled sequence. This gives you an aggregate view of team readiness.

This server touches user account information, including names, IDs, and associated organizational details pulled via `list_users` and `get_org_summary`.

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