How do I get a Delighted API Key?

Log in to your Delighted account, navigate to **Settings > API**, and you can retrieve your unique API Key from that section.

Can I see real-time NPS updates?

Yes, you can use the get_nps_metrics_summary tool to see the latest calculated score and breakdown of responses.

Does the integration support multiple survey types?

Yes, Delighted supports NPS, CSAT, CES, and other survey types. The agent will retrieve responses regardless of the survey methodology used in your account.

Delighted MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Delighted
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Delighted through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Delighted Assistant",
            instructions=(
                "You help users interact with Delighted. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Delighted"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Delighted MCP Server

Integrate Delighted by Qualtrics, the leading experience management platform, directly into your AI workflow. Monitor your customer feedback in real-time, track Net Promoter Score (NPS) metrics, and analyze survey comments using natural language.

The OpenAI Agents SDK auto-discovers all 10 tools from Delighted through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Delighted, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Feedback Monitoring — List and retrieve detailed survey responses, including scores and text comments from your customers.
Metric Intelligence — Retrieve overall NPS metrics, including promoter, passive, and detractor counts.
Customer Research — Access feedback history and metadata for specific individuals in your database.
Survey Automation — Add new people to Delighted to trigger feedback surveys directly via chat.

The Delighted MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Delighted to OpenAI Agents SDK via MCP

Follow these steps to integrate the Delighted MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Delighted

Why Use OpenAI Agents SDK with the Delighted MCP Server

OpenAI Agents SDK provides unique advantages when paired with Delighted through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Delighted + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Delighted MCP Server delivers measurable value.

Automated workflows: build agents that query Delighted, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Delighted, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Delighted tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Delighted to resolve tickets, look up records, and update statuses without human intervention

Delighted MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Delighted to OpenAI Agents SDK via MCP:

add_person_to_survey

Adds a new person to the system and schedules a survey invitation to be sent via the default channel. Add a new person to Delighted to trigger a survey

get_nps_metrics_summary

Returns real-time Net Promoter Score (NPS) along with a breakdown of promoters, passives, and detractors. Retrieve overall NPS metrics, including promoter and detractor counts

get_person_feedback_history

Resolves all previous survey responses, cumulative NPS contribution, and associated person attributes. Get all feedback and metadata for a specific person

get_recent_customer_comments

List the most recent survey responses that include a text comment

get_response_details

Resolves customer details, specific survey channel, and the full text of the feedback comment. Get full details for a specific survey response

list_feedback_contacts

Returns a list of people who have interacted with Delighted, including their email addresses and survey history metadata. List people who have been sent surveys or provided feedback

list_recent_detractors

Identifies "detractors" based on an NPS score between 0 and 6. Identify customers who provided a low NPS score (0-6)

list_survey_responses

Returns response metadata including score, comment, person identifier, and timestamp. List all customer survey responses in Delighted

list_top_promoters

Identifies "promoters" based on an NPS score of 9 or 10. Identify customers who provided a high NPS score (9-10)

search_responses_by_comment

Identifies survey responses where the text matches the provided search term. Search for survey responses containing specific keywords in comments

Example Prompts for Delighted in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Delighted immediately.

"What is our current NPS score?"

"Show me the last 5 customer comments containing 'pricing'."

"Get the feedback history for 'user@example.com'."

Troubleshooting Delighted MCP Server with OpenAI Agents SDK

Common issues when connecting Delighted to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Delighted + OpenAI Agents SDK FAQ

Common questions about integrating Delighted MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.