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

Q: What configuration does the Highlight (Session Replay & UX) MCP Server require in Windsurf?

You need to add the server configuration to your /.codeium/windsurf/mcpconfig.json file under the mcpServers key. Make sure your environment variables contain your Highlight project credentials before launching Cascade.

Q: Can Windsurf resolve complex trace issues using Highlight (Session Replay & UX)?

Yes, Cascade chains the ingestotlptraces tool with local file editing to fix issues end-to-end. It reads the telemetry from Highlight, locates the bug in your codebase, and writes the patch automatically.

Feed live telemetry directly into your Windsurf Cascade workspace to fix frontend bugs in real time.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace frontend bugs inside Windsurf

The `ingest_otlp_traces` tool sends OpenTelemetry trace data directly to Highlight so Cascade can map backend errors to actual user sessions. When a user reports a broken checkout button, Cascade queries this tool, correlates the session replay, and points you to the exact line of failing code. Cascade handles the multi-step sequence of scanning the trace, finding the operation ID, and pulling the trace payload. You get the exact stack trace in your sidebar without manually searching through independent monitoring platforms.

Send app telemetry with this MCP Server

The `ingest_otlp_logs` tool transmits structured JSON logs containing your target `highlight.project_id` to link backend warnings with visual session recordings. Cascade parses these structured logs to understand the system state before a crash occurs. By feeding structured telemetry directly into the IDE, your agent diagnoses state synchronization bugs instantly. You don't have to copy-paste log blocks from your terminal to explain the context to your editor.

Parse raw console output instantly

The `ingest_raw_log` tool processes unstructured text strings and formats them into clean, Highlight-compatible log envelopes. If Cascade encounters an unhandled exception during a local run, it uses this tool to forward the raw terminal output directly to your session dashboard. This mechanism bridges the gap between raw local terminal outputs and cloud-based session replays. Your autonomous agent checks the raw log, matches it with active sessions, and updates the code to prevent the error.

Setup guide

Set up Highlight (Session Replay & UX) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Highlight (Session Replay & UX) MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Highlight (Session Replay & UX) payment history." If connected, Cascade will call the Highlight (Session Replay & UX) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses this MCP Server to pull trace and log data directly into your active workspace. It maps these backend events to visual sessions, letting Cascade pinpoint the exact lines of code causing UI rendering failures.

You need to add the server configuration to your `~/.codeium/windsurf/mcp_config.json` file under the `mcpServers` key. Make sure your environment variables contain your Highlight project credentials before launching Cascade.

Yes, Cascade chains the `ingest_otlp_traces` tool with local file editing to fix issues end-to-end. It reads the telemetry from Highlight, locates the bug in your codebase, and writes the patch automatically.

No, Vinkius manages the authentication layer using a single endpoint token. Windsurf connects securely to the sandbox, and all your tool calls execute without requiring individual API keys for each request.

The MCP server runs inside an ephemeral, zero-trust V8 isolate sandbox that processes your raw text strings, OTLP logs, and traces securely. No data persists in the sandbox after the tool execution completes, keeping your telemetry data private.

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