How to Use the Loop MCP in LlamaIndex

Q: How do I index Loop feedback data inside LlamaIndex?

Use llama-index-tools-mcp to connect to the Vinkius server endpoint. Once connected, your agent can call listfeedback and load the resulting text directly into your document index for vector search.

Q: Can LlamaIndex agents run tools like addinternalnote?

Yes, you convert the MCP tools into tool specs using McpToolSpec. Pass these to your FunctionAgent so it can write notes or pull metrics dynamically during a query.

Q: Does the LlamaIndex integration support live sentiment queries?

Absolutely, your agent can call getsentimentmetrics on demand. This ensures that any RAG search regarding customer health is based on live, up-to-the-minute scores rather than stale database dumps.

Q: Can I filter which tools the agent has access to?

Yes, you can use the allowedtools filter when setting up your tool spec. This lets you restrict your agent to read-only actions like listprojects if you want to prevent accidental writes.

Index live Loop sentiment metrics and NPS data directly into your LlamaIndex vector stores for RAG queries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Loop MCP to LlamaIndex

Create your Vinkius account to connect Loop 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 Loop with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex RAG queries in this MCP Server

Index the live output of `list_feedback` directly into a LlamaIndex vector store to make customer sentiment searchable. Your agent can query past feedback sessions to find historical patterns instead of guessing why users are churn risks. This integration turns raw customer metrics into a dynamic knowledge base. When a user asks about recent complaints, the agent pulls fresh data using `get_sentiment_metrics` to ground its response in actual numbers.

Search and cluster recurring customer themes

Retrieve the main issues users are facing by calling `list_feedback_themes` and indexing those themes for semantic search. This setup eliminates manual categorization of support tickets. When a new bug report comes in, LlamaIndex matches it against these indexed themes. If a match is found, the agent uses `add_internal_note` to link the new feedback to the existing cluster, keeping your product team organized.

Map developer tickets to user sentiment trends

Fetch active engineering tasks via `list_dev_tickets` to connect development work directly to customer experience trends. This MCP Server lets your agent fetch active engineering tasks and cross-reference them with actual customer complaints. By calling `get_ticket_details`, the agent evaluates whether a planned fix addresses the issues found in `get_sentiment_metrics`. It helps you prioritize your engineering backlog based on real user frustration.

Setup guide

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

Use `llama-index-tools-mcp` to connect to the Vinkius server endpoint. Once connected, your agent can call `list_feedback` and load the resulting text directly into your document index for vector search.

Yes, you convert the MCP tools into tool specs using `McpToolSpec`. Pass these to your `FunctionAgent` so it can write notes or pull metrics dynamically during a query.

Absolutely, your agent can call `get_sentiment_metrics` on demand. This ensures that any RAG search regarding customer health is based on live, up-to-the-minute scores rather than stale database dumps.

Yes, you can use the `allowed_tools` filter when setting up your tool spec. This lets you restrict your agent to read-only actions like `list_projects` if you want to prevent accidental writes.

Yes, Vinkius runs this MCP Server in an isolated, zero-trust V8 sandbox. Your raw customer feedback and sentiment scores are processed in memory and never persisted on Vinkius infrastructure, ensuring complete data privacy.

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