How do I connect my Highlight project?

You need to provide your Highlight Project ID after subscribing to the MCP on Vinkius. Once connected, your AI client can start sending data immediately.

What kind of logs can I send?

You can send raw text-based logs or structured OTLP JSON logs. The MCP supports both simple messages and complex, metadata-rich payloads.

Can I send traces as well as logs?

Yes, the MCP includes a specific capability for ingesting OTLP JSON traces to help you visualize request flows.

Which AI clients can use this MCP?

Any MCP-compatible client works, including Claude, Cursor, Windsurf, and VS Code.

Do I need to format JSON manually?

No, you can tell your AI agent to send the data, and it will use the appropriate capabilities to format and ingest the logs or traces for you.

How can I send a basic text log message to my dashboard?

You can use the ingest_raw_log capability. Simply provide the service name and the message content, and it will be sent directly to Highlight.

Does this server support structured OpenTelemetry logs?

Yes! Use the ingest_otlp_logs capability to send structured logs in OTLP JSON format. Ensure your payload includes the project ID attribute.

Can I visualize request traces using this integration?

Absolutely. The ingest_otlp_traces capability allows you to send OTLP JSON traces to Highlight, helping you track request spans and performance.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Highlight Session Replay UX to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Send logs and traces to your dashboard via your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Highlight.

01
Ingest raw log
This capability sends a single raw log message into your Highlight project. It is the fastest way to push text-based backend logs to your dashboard.
02
Ingest otlp logs
This capability handles structured OTLP JSON logs. It requires a highlight.project_id to ensure the logs land in the right place with all their metadata.
03
Ingest otlp traces
This capability pushes OTLP JSON traces to Highlight. Use it to map out request flows and pinpoint performance bottlenecks.

Real work

What teams actually run

Local Debugging

Send logs from your local machine to the Highlight dashboard to see how your code behaves in real time.

Performance Bottleneck Hunting

Push OTLP traces to visualize how requests move through your system and where they slow down.

Automated Telemetry

Use your agent to ingest structured OTLP JSON logs to keep your observability data rich and organized.

UX Friction Analysis

Link backend errors to specific user sessions to understand why a user experience is failing.

Automate a task

Put Highlight to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Highlight works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Highlight to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

968ms average. Fast in production.

Highlight is checked daily against the live service.

Daily averagePeak 1285ms

Oct 3Today

Fastest day: 745ms
Slowest day: 1285ms
14-day trend: Stable0%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Highlight, so you can see the experience inside your AI.

It does not authenticate your account with Highlight. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Highlight Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_NSOfm3XYtPzM2Hc98HN4tUV10V3ARA5UYzOvTYCR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Highlight capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "highlight-session-replay-ux-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_NSOfm3XYtPzM2Hc98HN4tUV10V3ARA5UYzOvTYCR/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Highlight in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Highlight owners hand off.

This MCP is built for technical teams who need to bridge the gap between their code and their observability dashboard.

01
Developers
They use the agent to push logs from local environments to Highlight for quick debugging.
02
DevOps Engineers
They automate the ingestion of structured OTLP data to increase system visibility.
03
Product Managers
They correlate backend logs with user sessions to find where users are struggling.

FAQ

Questions Highlight owners ask.

01
How do I connect my Highlight project?
You need to provide your Highlight Project ID after subscribing to the MCP on Vinkius. Once connected, your AI client can start sending data immediately.
02
What kind of logs can I send?
You can send raw text-based logs or structured OTLP JSON logs. The MCP supports both simple messages and complex, metadata-rich payloads.
03
Can I send traces as well as logs?
Yes, the MCP includes a specific capability for ingesting OTLP JSON traces to help you visualize request flows.
04
Which AI clients can use this MCP?
Any MCP-compatible client works, including Claude, Cursor, Windsurf, and VS Code.
05
Do I need to format JSON manually?
No, you can tell your AI agent to send the data, and it will use the appropriate capabilities to format and ingest the logs or traces for you.
06
How can I send a basic text log message to my dashboard?
You can use the ingest_raw_log capability. Simply provide the service name and the message content, and it will be sent directly to Highlight.
07
Does this server support structured OpenTelemetry logs?
Yes! Use the ingest_otlp_logs capability to send structured logs in OTLP JSON format. Ensure your payload includes the project ID attribute.
08
Can I visualize request traces using this integration?
Absolutely. The ingest_otlp_traces capability allows you to send OTLP JSON traces to Highlight, helping you track request spans and performance.

Explore

More in Developer Tools

Connect Highlight to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Ingest raw log

Ingest otlp logs

Ingest otlp traces

What teams actually run

Local Debugging

Performance Bottleneck Hunting

Automated Telemetry

UX Friction Analysis

Building your own app? The connector is yours to use.

Highlight Connector

Claude Desktop

Developers

DevOps Engineers

Product Managers

How do I connect my Highlight project?

What kind of logs can I send?

Can I send traces as well as logs?

Which AI clients can use this MCP?

Do I need to format JSON manually?

How can I send a basic text log message to my dashboard?

Does this server support structured OpenTelemetry logs?

Can I visualize request traces using this integration?

Loggly (Cloud Log Management API) AI Connector

Logflare (Log Management Analytics) AI Connector

Logstash (Server-side Log Pipeline API) AI Connector

Amazon CloudWatch Log Group AI Connector

Suggestions

Sumo Logic AI Connector

Google Cloud Logging Stream AI Connector

Condition Observation Log AI Connector

Azure Log Analytics Workspace AI Connector