How to Use the Delighted MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system automatically email Delighted detractors?

Yes. Your agent calls listrecentdetractors to find low scores. It then drafts and sends emails using your existing communication tools based on the specific feedback.

Q: How do I find specific product feedback in Delighted with OpenAI Agents SDK?

Prompt your agent to run searchresponsesbycomment with specific keywords. It returns all matching text comments so your agent can summarize feature requests or bug reports.

Connect Delighted to your OpenAI Agents SDK system. Build production-ready agents that track NPS scores and trigger surveys automatically.

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 OpenAI Agents SDK

Create your Vinkius account to connect Delighted to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

NPS Triage with OpenAI Agents SDK

The `get_nps_metrics_summary` tool feeds real-time sentiment data directly into your agent's context window. Your primary router agent reads the promoter and detractor breakdown, then hands off the execution to specialized sub-agents based on the score. Built-in guardrails validate the output before taking action. If a score drops below a specific threshold, the agent pulls exact comments using `get_recent_customer_comments` and logs the incident in your tracking system without hallucinating the metrics.

Automate Detractor Recovery

Finding unhappy customers requires calling `list_recent_detractors` to pull profiles with scores between 0 and 6. The agent retrieves the specific complaint via `get_response_details` to understand exactly why the user gave a low rating. OpenAI's tracing dashboard records every API call your agent makes to the MCP Server. You see exactly which customer profiles the agent evaluated before drafting an apology email or triggering a support ticket.

Context-Aware Survey Triggers

Adding new users to your feedback loop happens through the `add_person_to_survey` tool. Your agent detects when a user completes a major milestone in your app, then immediately schedules an invitation via their default channel. You avoid spamming users by checking `get_person_feedback_history` first. The agent verifies previous interactions and cumulative NPS contributions to ensure the customer hasn't already received a survey this month.

Setup guide

Set up Delighted MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Delighted tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Delighted tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Delighted tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Delighted Agent",
            instructions="You have access to Delighted tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using pip install openai-agents. Initialize the MCP Server via MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to the mcp_servers array in your Agent constructor.

Yes. Your agent calls list_recent_detractors to find low scores. It then drafts and sends emails using your existing communication tools based on the specific feedback.

Setting cacheToolsList=True during initialization improves startup performance. The agent auto-discovers all ten available tools on the first run and caches the definitions.

Prompt your agent to run search_responses_by_comment with specific keywords. It returns all matching text comments so your agent can summarize feature requests or bug reports.

Your agent accesses PII like email addresses and raw survey comments. Vinkius runs the MCP Server in an ephemeral V8 Isolate sandbox, meaning data passes through to your OpenAI environment without being stored on our infrastructure.

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