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

Q: How do I configure Highlight (Session Replay & UX) for a CrewAI agent?

Use pip install crewai "crewaitools". Pass the server URL directly into the mcps array on your agent definition for instant access.

Q: Why is my CrewAI agent failing to send OTLP logs to Highlight (Session Replay & UX)?

Check the payload structure. The ingestotlplogs tool strictly requires the highlight.projectid attribute. If your agent omits it, the request drops.

Give your CrewAI agents the ability to push traces and raw logs straight to Highlight for autonomous session monitoring.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Trace Ingestion

At every handoff between agents, your crew uses the `ingest_otlp_traces` tool on this MCP server to push OTLP JSON traces. Visual timelines of your crew's decision-making process appear inside Highlight. Stop guessing which agent dropped the ball and start reading the actual trace data.

CrewAI MCP Server Raw Logging

The `ingest_raw_log` tool allows any agent in your CrewAI setup to ship unstructured text directly to your observability stack. Bypassing complex schema definitions saves time. An agent hits an edge case, fires off a quick raw log, and you see it attached to the user's session replay immediately.

Structured OTLP Logs for Teams

Enterprise monitoring requires the `ingest_otlp_logs` tool to format your CrewAI team's operational data into OTLP JSON. Make sure the agent includes the `highlight.project_id` attribute. Integrating your autonomous operations with existing engineering dashboards puts your crew's output right next to your backend server logs.

Setup guide

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

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Highlight (Session Replay & UX) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Highlight (Session Replay & UX) Analyst",
    goal="Access and analyze Highlight (Session Replay & UX) data via MCP.",
    backstory="Expert analyst with direct Highlight (Session Replay & UX) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Highlight (Session Replay & UX) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Highlight (Session Replay & UX) Analyst",
        goal="Access and analyze Highlight (Session Replay & UX) data via MCP.",
        backstory="Expert analyst with direct Highlight (Session Replay & UX) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Highlight (Session Replay & UX) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Use pip install crewai "crewai[tools]". Pass the server URL directly into the mcps array on your agent definition for instant access.

You can assign the ingestion tools to a dedicated monitoring agent, or give the MCP server to every agent in the crew for distributed logging.

Check the payload structure. The ingest_otlp_logs tool strictly requires the highlight.project_id attribute. If your agent omits it, the request drops.

Your manager agent can push traces summarizing the entire crew's execution, while worker agents push raw logs for their individual tasks.

The execution explicitly handles raw log messages and OTLP structured JSON. Vinkius runs the connection through a strict V8 Isolate Sandbox. No data persists locally, and the execution context is destroyed the millisecond the log transmission completes.

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