How to Use the Loop MCP in LangChain

Q: How do I pass Loop tools to a LangChain agent?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with the Vinkius endpoint. From there, call client.gettools() to extract the tools and pass them directly into your createagent method.

Q: Can I trace Loop API latency inside LangChain?

Yes, every call to tools like getsentimentmetrics is fully tracked if you have LangSmith enabled. You will see the exact execution time, input parameters, and output payloads in your tracing dashboard.

Feed real-time customer NPS and CSAT data directly into your LangChain reasoning loops to automate support triage.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Loop MCP to LangChain

Create your Vinkius account to connect Loop 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 Loop with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Loop feedback metrics into LangChain pipelines

Feed the output of `get_sentiment_metrics` directly into your LangChain decision chain to let your agent automatically flag accounts showing sudden drops in satisfaction. The agent inspects the customer scores, isolates the bad ratings, and decides whether to escalate. You don't have to write custom glue code to link these steps. This MCP Server handles the output of `list_feedback` as a direct input for the next node in your graph, letting you build self-correcting support loops that trigger without human intervention.

Trace feedback triage paths with LangSmith

Track every step of your feedback triage when your agent calls `list_feedback_themes` to group incoming complaints. LangSmith traces every step of that execution, showing you the exact token count, raw JSON payload, and API latency inside your developer dashboard. This visibility keeps your production runs predictable. If an agent tries to run `add_internal_note` on a closed ticket, you can pinpoint the exact moment the chain went sideways and adjust your prompt logic immediately.

Auto-escalate technical bugs to engineering queues

Let your agent run `list_dev_tickets` to instantly match customer complaints against known engineering issues. It uses `get_ticket_details` to check if a fix is already in progress before bugging your development team. If it's a new bug, the agent uses `add_internal_note` to brief your developers with raw sentiment context. It does all of this in a single, observable run, keeping your engineering team aligned with actual user pain points.

Setup guide

Set up Loop 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 Loop 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({
    "loop-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 Loop 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 Loop. 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 Loop 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 Loop MCP in LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with the Vinkius endpoint. From there, call `client.get_tools()` to extract the tools and pass them directly into your `create_agent` method.

Yes, every call to tools like `get_sentiment_metrics` is fully tracked if you have LangSmith enabled. You will see the exact execution time, input parameters, and output payloads in your tracing dashboard.

The framework treats each MCP tool as a potential action in a ReAct loop. Your agent can first call `list_feedback` to find recent complaints, inspect the details, and then decide to run `add_internal_note` based on what it finds.

By default, the connection is stateless, which works perfectly for quick cron jobs. If you need to keep user context across multiple steps, use `client.session()` to manage a persistent connection.

All feedback metrics and customer notes stay securely inside the Vinkius V8 sandbox during execution of this MCP Server. We never store your raw NPS scores or CSAT text on our servers, and the sandbox is destroyed the moment your agent finishes its run.

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