How to Use the GetFeedback MCP in LlamaIndex

Q: Can LlamaIndex search through old GetFeedback survey responses?

Yes. You write a script that iterates through listfeedbackpage and dumps the output into your vector store. Your query engine then performs semantic search over the entire historical dataset.

Q: How does LlamaIndex handle live GetFeedback stats?

You give your agent access to getsurveystats. When a user asks for completion rates, the agent skips the vector store and queries the live API directly to get the current number.

Index live survey responses into your LlamaIndex knowledge base.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GetFeedback MCP to LlamaIndex

Create your Vinkius account to connect GetFeedback 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 GetFeedback with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest GetFeedback MCP Server Data

The GetFeedback MCP Server feeds raw survey records directly into LlamaIndex. You query `list_survey_responses` to pull historical feedback, and LlamaIndex chunks that text into your vector store. Your application now searches actual customer sentiment instead of relying on outdated static files. You keep the index fresh without manual exports. Your data pipeline calls `list_recent_feedback` on a schedule, embedding only the newest submissions. When a user asks about recent product complaints, the query engine retrieves exact quotes from the live API.

Ground Queries in Real Survey Stats

Your RAG application needs hard numbers to back up semantic search results. By exposing `get_survey_stats` to your query engine, the agent retrieves the exact response count and completion rates. It answers questions using accurate mathematical baselines. You add context to those numbers with `get_survey_details`. The agent pulls the survey structure and question metadata, linking specific user answers back to the exact prompt they read. This prevents the LLM from misinterpreting a low score out of context.

Map Responses to User Identities

You need to know who is talking. The agent uses `get_my_identity` to verify the current context, then pulls specific user records via `get_response_details`. LlamaIndex maps these individual responses to your broader customer knowledge graph. This setup allows for highly targeted semantic searches. You can filter the vector store for completed entries using `list_completed_feedback`, ensuring your query engine only processes finalized opinions instead of partial drafts.

Setup guide

Set up GetFeedback 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 GetFeedback 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 GetFeedback tools.",
)
response = await agent.run("List recent GetFeedback 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 GetFeedback. 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 GetFeedback 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 GetFeedback MCP in LlamaIndex

Install llama-index-tools-mcp. Initialize a BasicMCPClient with your endpoint URL, wrap it in McpToolSpec, and call to_tool_list_async(). Pass those tools directly into your FunctionAgent.

Yes. You write a script that iterates through list_feedback_page and dumps the output into your vector store. Your query engine then performs semantic search over the entire historical dataset.

You give your agent access to get_survey_stats. When a user asks for completion rates, the agent skips the vector store and queries the live API directly to get the current number.

Only if you explicitly allow it. You can filter the tool list to exclude send_survey_invites when setting up your McpToolSpec, keeping your agent strictly in read-only mode.

The integration touches exact email addresses and written feedback. The Vinkius zero-trust architecture ensures this data travels through a single-use container. Once LlamaIndex embeds the text into your local vector store, the transport environment is destroyed immediately.

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