How to Use the Delighted MCP in LangChain

Q: Can my LangChain agent search through historic customer comments in Delighted?

Yes, your agent can run searchresponsesbycomment to find specific keywords across historical feedback. This allows your chain to look for patterns, like recurring mentions of a bug, and compile a report.

Q: How does the Delighted integration handle LangSmith tracing?

Every tool run, like getresponsedetails, is recorded as a step in your LangChain run. You can see the exact input parameters, the raw JSON payload returned, and how long the API took to respond.

Get your LangChain agents reacting to real-time NPS shifts and scheduling customer surveys via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Delighted MCP to LangChain

Create your Vinkius account to connect Delighted 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 Delighted with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run feedback loops directly in your LangChain graphs

By calling `get_recent_customer_comments` and `get_nps_metrics_summary`, your agent pulls raw customer sentiment data mid-execution. If a customer leaves a bad score, the agent spots it immediately, branches the logic, and flags the account before your morning coffee cools. You get full visibility into this flow with LangSmith tracing. Every tool execution is tracked, showing you exactly when your agent decided to inspect a rating and how it parsed the score. No more guessing why a customer was flagged; the entire decision tree is laid out in your logs.

Automate survey distribution based on chain events

By calling `add_person_to_survey`, your agent can queue up an NPS questionnaire right after a specific interaction. If your chain completes a support ticket or onboarding flow, the agent handles the follow-up setup instantly. Because this MCP integration works with standard LangChain adapters, you can mix this tool with 500 other integrations. You could pull a user's ID from a database, check their status, and schedule the survey in a single, unified pipeline.

Track detractors and route them to support

By calling `list_recent_detractors` to pull a list of accounts with scores under seven, your agent can then use `get_person_feedback_history` to pull their full context. This isn't just about reading data; it's about giving your agent the historical background to write a personalized recovery email. The agent analyzes their cumulative score contribution and past comments in one run. Your LangChain agent can construct a tailored response that references their specific pain points, turning a bad review into an opportunity to fix things.

Setup guide

Set up Delighted 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 Delighted 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({
    "delighted-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 Delighted 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 Delighted. 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 Delighted 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 Delighted MCP in LangChain

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient pointing to the Vinkius endpoint, pull the tools with client.get_tools(), and pass them directly to your agent constructor.

Yes, your agent can run search_responses_by_comment to find specific keywords across historical feedback. This allows your chain to look for patterns, like recurring mentions of a bug, and compile a report.

Every tool run, like get_response_details, is recorded as a step in your LangChain run. You can see the exact input parameters, the raw JSON payload returned, and how long the API took to respond.

You can load multiple servers into your client wrapper. Your agent can query this server to find a detractor and then immediately use a database tool to update that user's status.

Vinkius runs the MCP Server in an isolated sandbox, meaning your customer emails and NPS scores are never cached. The endpoint acts as a secure pass-through directly to the API, using your token for instant, ephemeral data retrieval.

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