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

Q: What happens if I forget the project ID in Highlight (Session Replay & UX) via Mastra AI?

The ingestotlplogs tool drops the data. You must include the highlight.projectid attribute in the JSON payload for the ingestion to succeed.

Wire up your Mastra AI workflows to push OTLP traces and logs directly into Highlight for immediate session debugging.

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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Workflow Failures with Traces

When steps fail and trigger exponential backoffs, the `ingest_otlp_traces` tool lets your Mastra AI workflow push JSON traces directly to Highlight. You get a clear map of exactly which branch executed and where the timeout happened. The agent logs the trace, allowing you to correlate it to the exact user session that triggered the workflow.

Push Raw Logs on Retry

Your Mastra AI agent calls the `ingest_raw_log` tool to fire off a simple text message right before a retry kicks off. Zero configuration is required here. The agent just ships the raw string. Watch the Highlight console to see exactly how many times the workflow looped before succeeding.

Mastra AI MCP Server OTLP Ingestion

Formatting your Mastra AI agent telemetry into standard OTLP JSON happens through the `ingest_otlp_logs` tool on this MCP Server. Ensure the `highlight.project_id` is attached to the payload. This ties your agent's background operations directly to frontend user sessions. A customer complains about a broken checkout, and you pull up the exact OTLP log from the Mastra workflow.

Setup guide

Set up Highlight (Session Replay & UX) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Highlight (Session Replay & UX) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "highlight-session-replay-ux-mcp-client",
  servers: {
    "highlight-session-replay-ux-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Highlight (Session Replay & UX) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Highlight (Session Replay & UX) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Highlight (Session Replay & UX) transactions"
);
console.log(result.text);

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 Mastra AI

Install @mastra/mcp@latest. Create a new MCPClient instance with the server URL, then call mcpClient.listTools() and spread them into your agent's tool array to add this MCP Server.

If a tool call to the server fails due to network issues, Mastra's built-in workflow engine automatically backs off and tries the ingestion again.

The ingest_otlp_logs tool drops the data. You must include the highlight.project_id attribute in the JSON payload for the ingestion to succeed.

Mastra supports requireToolApproval natively. If you want a human in the loop before shipping a massive OTLP trace, you pause the workflow.

The server processes OTLP trace payloads and raw log strings. Authentication is handled entirely via a single endpoint token in an ephemeral, zero-trust container. The server spins up, routes the telemetry to Highlight, and immediately shuts down.

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