How to Use the Delighted MCP in LlamaIndex

Q: Can LlamaIndex query historic feedback from Delighted?

Yes, the agent can call listfeedbackcontacts to get a list of users, then fetch and index their individual feedback histories. This makes past feedback searchable alongside your internal wikis and documents.

Q: Can I limit which tools the agent can access?

You can use the allowedtools filter when setting up the client. This lets you restrict your agent to only read tools like listtoppromoters while hiding write operations.

Index live customer feedback and NPS scores directly into your LlamaIndex RAG pipelines with 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 LlamaIndex

Create your Vinkius account to connect Delighted to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Use this MCP Server to index customer feedback

By calling `list_survey_responses`, your LlamaIndex agent can fetch live records and index them into a vector store. This turns your customer comments into a queryable knowledge base. Your agent can then perform semantic searches to find underlying customer trends that a simple keyword search would miss. By combining live API data with your existing documents, you build a RAG application that actually understands how users feel. When you ask your agent about product friction points, it pulls actual feedback to back up its answers.

Feed real-time NPS metrics into your agent's context

The tool `get_nps_metrics_summary` retrieves the latest promoter and detractor counts, allowing your agent to convert raw data into indexable nodes. It keeps your agent's general knowledge about customer satisfaction accurate and updated. This live context helps prevent hallucinations, relying on the real-time numbers retrieved by the MCP Server rather than guessing based on outdated static training data.

Retrieve full customer profiles for context-rich queries

Your agent can use `get_person_feedback_history` to pull a user's entire journey, including their history and metadata. LlamaIndex then packages this history into the LLM prompt context. This gives your agent a complete picture before it answers. If you ask why a specific user is unhappy, the agent pulls their history via `get_response_details` to give you a detailed, context-aware explanation.

Setup guide

Set up Delighted MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Delighted MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Delighted tools.",
)
response = await agent.run("List recent Delighted data")

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 LlamaIndex

Install llama-index-tools-mcp and set up the BasicMCPClient. Convert the server tools using McpToolSpec and pass them to your FunctionAgent to start indexing feedback.

Yes, the agent can call list_feedback_contacts to get a list of users, then fetch and index their individual feedback histories. This makes past feedback searchable alongside your internal wikis and documents.

The agent uses its reasoning loop to determine if its indexed data is stale. If a user asks for the latest metrics, it will automatically invoke get_nps_metrics_summary to refresh its context.

You can use the allowed_tools filter when setting up the client. This lets you restrict your agent to only read tools like list_top_promoters while hiding write operations.

Vinkius executes this MCP Server in a secure, zero-trust sandbox. Your customer comments and survey metrics are processed in memory and passed directly to LlamaIndex without any local persistent storage on our servers.

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