How to Use the Highlight (Session Replay & UX) MCP in LlamaIndex

Q: How do I connect Highlight (Session Replay & UX) to LlamaIndex?

Install llama-index-tools-mcp first. Set up a BasicMCPClient with your endpoint, wrap it in an McpToolSpec, and call totoollistasync() to feed it to your FunctionAgent.

Index your observability data and let LlamaIndex push structured OTLP traces straight into Highlight.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Highlight (Session Replay & UX) MCP to LlamaIndex

Create your Vinkius account to connect Highlight (Session Replay & UX) 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 Highlight (Session Replay & UX) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed LlamaIndex agents trace tools

The Highlight MCP Server equips your LlamaIndex workflow with direct write access to your observability stack. When your RAG application detects an anomaly in indexed documentation, it triggers `ingest_raw_log` to record the event. The agent maps the error back to the user's active session. This bridges the gap between your vector store and your frontend monitoring. You get grounded logs based on actual semantic search results rather than generic error codes.

Structure OTLP logs from queries

Agents synthesize answers from past session transcripts and push the metadata back as structured telemetry. By calling `ingest_otlp_logs`, the system sends OTLP JSON directly to Highlight. You just have to make sure the agent includes the `highlight.project_id` in the payload. The real value hits when you query past configurations. The agent compares historical data against the live environment and logs the delta. You stop guessing what changed and start reading the exact trace in your dashboard.

Map span hierarchies with traces

Complex RAG pipelines generate massive amounts of intermediate steps. Your agent uses `ingest_otlp_traces` to map these steps as individual spans within Highlight. You see exactly how long the embedding generation and vector retrieval took. Debugging hallucinated responses becomes trivial. You open the session replay, look at the trace hierarchy, and pinpoint exactly which document chunk caused the bad output.

Setup guide

Set up Highlight (Session Replay & UX) 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 Highlight (Session Replay & UX) 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 Highlight (Session Replay & UX) tools.",
)
response = await agent.run("List recent Highlight (Session Replay & UX) 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 Highlight. 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 Highlight (Session Replay & UX) 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 Highlight (Session Replay & UX) MCP in LlamaIndex

Install `llama-index-tools-mcp` first. Set up a `BasicMCPClient` with your endpoint, wrap it in an `McpToolSpec`, and call `to_tool_list_async()` to feed it to your `FunctionAgent`.

This specific server is built for ingestion, not retrieval. Your agent pushes data using tools like `ingest_otlp_logs`, which you then view inside the Highlight web dashboard.

Sometimes your RAG pipeline hits a retrieval failure that you want attached to a specific user session. The `ingest_raw_log` tool lets the agent dump that error state instantly without formatting JSON.

Your agent handles the formatting based on the schema exposed by the MCP endpoint. You just need to provide the raw context and instruct the agent to build the trace.

This MCP tool routes raw log strings and OTLP JSON payloads. Vinkius enforces a zero-trust architecture where the connection drops immediately after execution. Your API tokens stay isolated from the core RAG application memory.

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