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

Q: How do I load Highlight (Session Replay & UX) into AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with StreamableHttpServerParams to fetch the tools, then pass them to your AssistantAgent.

Q: Can multiple agents write to Highlight (Session Replay & UX) simultaneously?

Yes. Any agent with access to the ingestrawlog or trace tools can push data. The Highlight backend orders the incoming events based on their timestamps.

Let your AutoGen agents debate system anomalies and push consensus traces directly to Highlight.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Equip agents with the MCP Server

The Highlight MCP Server drops directly into your multi-agent conversations. A diagnostic agent can analyze a failing system state, argue with a performance agent about the root cause, and then call `ingest_otlp_logs` to record the final consensus. The payload automatically routes to your dashboard. You just have to ensure the agent includes the `highlight.project_id` attribute. Once that hits the API, your team gets a perfect record of the exact error context attached to the user's session replay.

Dump raw text from agent debates

Sometimes the agents cannot agree on a structured OTLP format. When the conversation stalls or hits a fallback state, the system can trigger `ingest_raw_log`. This pushes the raw text of the debate straight into Highlight. You read the raw log alongside the frontend session. Instead of scrolling through endless terminal output trying to figure out why the agents failed, you see their exact output synced with the user's cursor movements.

Build complex OTLP traces

Creating deep trace hierarchies takes work. In AutoGen, a dedicated telemetry agent can gather context from the ongoing debate, build a nested JSON trace, and execute `ingest_otlp_traces`. The other agents verify the structure before the tool call fires. This division of labor means your core logic agents never worry about observability schemas. They just report their state, and the telemetry agent maps those states into spans inside Highlight.

Setup guide

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

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Highlight (Session Replay & UX) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Highlight (Session Replay & UX)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Highlight (Session Replay & UX) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Highlight (Session Replay & UX)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Highlight (Session Replay & UX) data")
    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 AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tools, then pass them to your `AssistantAgent`.

We recommend creating a dedicated telemetry agent. This keeps your reasoning agents focused on problem-solving while the telemetry agent formats the payloads for `ingest_otlp_logs`.

Yes. Any agent with access to the `ingest_raw_log` or trace tools can push data. The Highlight backend orders the incoming events based on their timestamps.

The tool call will return an error to the conversational loop. The agents can read that error, adjust the JSON structure, and retry the ingestion automatically.

The server processes OTLP JSON logs and raw text strings generated by your agents. Vinkius operates this MCP connection in an ephemeral sandbox, meaning no conversational state or auth tokens persist after the session ends.

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