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

Q: How do I configure Highlight (Session Replay & UX) in the Claude Desktop configuration file?

Open your claudedesktopconfig.json file and add the server configuration under your MCP config key. Provide the executable path and arguments, ensuring your environment contains the correct project credentials before restarting the app.

Pipe raw logs and OTLP telemetry straight to Highlight from your Claude Desktop chat to instantly map backend errors to user sessions.

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 Claude Desktop

Create your Vinkius account to connect Highlight (Session Replay & UX) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send raw logs directly from Claude Desktop

The `ingest_raw_log` tool sends unstructured text strings directly from your local terminal session in Claude Desktop to your Highlight dashboard. When you paste a messy stack trace into your chat, Claude uses this MCP tool to instantly format and upload the raw text as a structured log event. This means you don't have to copy-paste logs into a web browser or run separate curl commands. Your agent parses the local output, calls the tool, and maps the error to your active session context without leaving the desktop interface.

Map OTLP traces inside your MCP Server

The `ingest_otlp_traces` tool pushes OpenTelemetry spans and trace hierarchies directly into Highlight to trace user sessions down to the database query. While chatting with Claude Desktop, you can ask your agent to analyze a slow local endpoint, and it immediately routes the trace payload to your project dashboard. This local execution relies on the desktop app's native stdio transport. The agent reads trace files from your local build directory, structures the JSON, and fires it off so you can see exactly where the frontend bottleneck happened.

Route OTLP logs with project identifiers

The `ingest_otlp_logs` tool transmits structured OTLP JSON logs to Highlight, requiring a valid `highlight.project_id` in the payload attributes. When you run local tests on Claude Desktop, your agent checks the config, appends the correct project ID, and uploads the logs. You don't have to manually configure environment variables for every single test run. The desktop client reads your local settings, applies the project ID, and ensures your telemetry data lands in the correct workspace.

Setup guide

Set up Highlight (Session Replay & UX) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Highlight (Session Replay & UX) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Highlight (Session Replay & UX) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under highlight-session-replay-ux-mcp.

json

{
  "mcpServers": {
    "highlight-session-replay-ux-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under your MCP config key. Provide the executable path and arguments, ensuring your environment contains the correct project credentials before restarting the app.

Yes, you can run it locally using stdio transport in your desktop app config, or connect to a remote URL via Claude Web integrations. The local setup works best when you need Claude to parse local log files from your machine.

Your desktop agent will display an error in the chat interface if the network request fails. Check your local network connection and check that the `highlight.project_id` is correctly formatted in your payload.

You don't need any extra SDKs installed on your local machine to run the server. Claude Desktop communicates directly with Highlight's APIs using standard HTTP requests triggered by the tools.

All logs, traces, and project IDs travel directly from your local machine to Highlight's endpoints. This MCP server runs locally in a sandbox, meaning no third party ever intercepts your telemetry payloads.

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