v0.1Iris MCP Server — 3 tools, 12 eval rules, open source

Blog

Research & insights

Original research on MCP agent observability, evaluation methodology, and the evolving landscape of AI agent infrastructure.

·Ian Parent

Agent Errors vs Application Errors: Why Your Error Tracker Can't See AI Failures

I have spent most of my career trusting error trackers. A TypeError fires, Sentry catches it, I get a Slack notification with a stack trace and breadcrumbs, and...

observabilityagentserror-trackingeval
·Ian Parent

MCP Meets OpenTelemetry: Bridging Agent Observability and Infrastructure Monitoring

There are two worlds in production observability right now, and they do not talk to each other.

opentelemetryobservabilitymcpinfrastructure
·Ian Parent

Toward an MCP Observability Specification

The Model Context Protocol defines how agents discover and invoke tools. It defines resources, prompts, and transport mechanisms. It standardizes the interface ...

mcpobservabilityspecificationprotocol
·Ian Parent

How to Evaluate AI Agent Output Without Calling Another LLM

Here is the default approach to evaluating agent output in 2026: take the output, send it to another LLM, ask that LLM to judge quality, and trust the result.

evalagentsmcptutorial
·Ian Parent

MCP Observability is the New APM

In 2010, application performance monitoring was a nice-to-have. Engineering teams shipped to production, watched their server logs, and hoped for the best. Moni...

observabilityapmmcpagents
·Ian Parent

Heuristic vs Semantic Eval: When <1ms Matters More Than LLM-as-Judge

There is a default assumption in the agent eval space right now: if you want to evaluate agent output, you need an LLM to judge it. Feed the output to GPT-4o wi...

evaluationheuristicllm-as-judgeperformance
·Ian Parent

The Cost of Invisible Agents: What $0.47 Per Query Looks Like at Scale

Last month I got a message from a developer running a research agent in production. His APM dashboard looked fine. HTTP 200s across the board. P99 latency under...

costobservabilityagentsmcp
·Ian Parent

Why Every MCP Agent Needs an Independent Observer

There is a sentence I keep coming back to. I first saw it from @aginaut on X:

observabilityagentsmcparchitecture
·Ian Parent

The State of MCP Agent Observability (March 2026)

The gap between deploying AI agents and understanding what they're doing.

observabilitymcpagentsreport
·Iris Team

Why Your AI Agents Need Observability

You shipped an AI agent. It works... sometimes. A user reports a wrong answer. Another says it took 40 seconds. A third notices it leaked an email address in it...

observabilityagentsmcpevaluation