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

Strictly validate observability data from Pydantic AI into Highlight (Session Replay & UX).

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe log ingestion for Pydantic AI

Your agent uses `ingest_otlp_logs` to send data that matches your expected schema. If the log structure is off, you'll know immediately. This prevents bad data from ever hitting your dashboard. It keeps your logs clean and your debugging sessions focused.

Trace spans with runtime validation

Use `ingest_otlp_traces` to ensure your trace spans are correctly formatted before they leave your agent. Pydantic AI checks the types at runtime. This is critical for complex agent systems. You get the peace of mind that your trace data is valid and useful for session replay.

Log raw strings with confidence

The `ingest_raw_log` tool provides a simple way to log unstructured data. Even then, the framework ensures the tool call is valid. It's a straightforward way to capture debug info. You get the benefit of Pydantic's validation even when the data itself isn't structured.

Setup guide

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

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "highlight-session-replay-ux-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Highlight (Session Replay & UX) tools.",
)

result = await agent.run("List recent Highlight (Session Replay & UX) transactions")
print(result.output)

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 Pydantic AI

You initialize an MCPToolset with your server's endpoint and pass it to your Agent instance. Pydantic AI then validates all tool interactions at runtime.

It does. If a tool call doesn't match the expected schema, the framework throws a validation error before the data is even sent to the server.

Yes. The server runs externally, and your agent connects via SSE or HTTP. This setup is perfect for testing your observability logic locally.

The tools are model-agnostic. Whether you use OpenAI, Anthropic, or a local model, the server handles the ingestion consistently.

The server only touches the log messages, trace spans, and project ID strings you pass through the tool arguments. No other agent memory is accessed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.