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

Q: How do I configure Highlight (Session Replay & UX) with LangChain?

Run pip install langchain-mcp-adapters langgraph. Then initialize a MultiServerMCPClient pointing to your Highlight server URL. Pass the resulting tool list to your createagent function.

Q: Can LangChain agents automatically format logs for Highlight (Session Replay & UX)?

Yes. ReAct agents inspect the schema for ingestotlplogs and structure the JSON accordingly. Just ensure your prompt instructs the agent to include the required highlight.projectid attribute.

Q: What is the difference between raw logs and OTLP traces in Highlight (Session Replay & UX) via LangChain?

The ingestrawlog tool accepts flat text strings for quick debugging. The ingestotlptraces tool requires structured OTLP JSON, which gives you granular span hierarchies in the Highlight UI.

Build observability pipelines in LangChain that pipe OTLP traces and raw logs directly to your Highlight dashboard.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe telemetry through the MCP Server

The Highlight MCP Server gives your LangChain agents direct access to log ingestion endpoints. Your ReAct agent grabs an error payload, formats it, and fires `ingest_otlp_logs` to push it straight into your project. You just need to pass the `highlight.project_id` attribute in the JSON payload. Chaining these steps means you stop manually formatting trace data. The agent pulls context from a database, builds the OTLP trace, and calls `ingest_otlp_traces`. LangSmith tracks the exact latency of the tool call while Highlight processes the session replay.

Dump raw text into session context

Sometimes you just have unstructured text and no time to build a schema. Your LangChain pipeline can take that plain text output and hit `ingest_raw_log` to attach it to the current user session. This lets your agent log intermediate reasoning steps directly into Highlight. You get a unified view of what the user saw and what your agent did. Instead of digging through terminal stdout, you open the Highlight UI and watch the session replay alongside the raw log entries your agent dumped there.

Chain OTLP traces with databases

Agents excel at connecting disparate systems. Your setup can pull user metadata from Postgres, construct a valid OTLP JSON structure, and execute `ingest_otlp_traces`. The agent handles the data transformation while you focus on the actual logic. Multi-server aggregation makes this even more powerful. Combine this integration with a database MCP, and your agent automatically routes trace data from backend storage right to your frontend session monitoring.

Setup guide

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

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Highlight (Session Replay & UX) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "highlight-session-replay-ux-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Highlight (Session Replay & UX) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Run `pip install langchain-mcp-adapters langgraph`. Then initialize a `MultiServerMCPClient` pointing to your Highlight server URL. Pass the resulting tool list to your `create_agent` function.

Yes. ReAct agents inspect the schema for `ingest_otlp_logs` and structure the JSON accordingly. Just ensure your prompt instructs the agent to include the required `highlight.project_id` attribute.

The `ingest_raw_log` tool accepts flat text strings for quick debugging. The `ingest_otlp_traces` tool requires structured OTLP JSON, which gives you granular span hierarchies in the Highlight UI.

LangSmith automatically traces every tool invocation. You will see exactly how many milliseconds the `ingest_otlp_logs` request took to resolve against the Highlight API.

The server processes OTLP JSON traces and raw log text. Vinkius runs this connection inside an ephemeral V8 Isolate Sandbox. Your agent only transmits the specific log payloads you authorize, and memory clears instantly after the run.

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