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

Comparison

Iris vs Arize AI

MCP-native, zero-code observability vs enterprise-grade ML monitoring. Focused simplicity vs full-platform power.

TL;DR

Iris is an MCP server your agent discovers and uses automatically — zero code changes, zero SDK imports, one SQLite file for storage. Arize AI is a comprehensive ML observability platform with Phoenix (open-source) for self-hosted tracing and evaluation, plus Arize AX (cloud) for enterprise-grade monitoring with embedding drift detection, RBAC, and advanced analytics. If you're building with MCP-compatible agents and want the simplest possible setup, Iris gets you there in 60 seconds. If you need enterprise ML observability with drift detection, broad framework instrumentation, or advanced evaluation workflows, Arize is the more comprehensive platform.

Feature Comparison

Side by side.

FeatureIrisArize AI
Integration methodMCP config (zero code)OpenTelemetry SDK + auto-instrumentation
Self-hosting complexitySingle SQLite filePhoenix: pip install + PostgreSQL (production)
Performance overheadZero (no SDK in hot path)OpenTelemetry collector + SDK in application
Eval capabilities12 built-in + 8 custom types, heuristic (<1 ms)LLM-as-Judge, custom evaluators, agent eval templates
Cost trackingPer-trace USD costToken and cost tracking across models
MCP supportProtocol-native (IS an MCP server)Phoenix MCP server (query traces, manage prompts)
LicenseMIT (fully permissive)Phoenix: Elastic License 2.0 (ELv2)
Embeddings & driftNot includedAdvanced embedding drift detection across NLP, CV, multi-modal
DashboardReal-time dark-mode UIFull-featured dashboards, Prompt IDE, Alyx AI assistant
Framework supportAny MCP-compatible agent20+ frameworks (OpenAI, LangGraph, CrewAI, LlamaIndex, DSPy, etc.)
Prompt managementNot includedPrompt IDE with versioning and optimization
Enterprise featuresRoadmap (v0.5)RBAC, SOC 2, online evals, Alyx assistant
PricingFree and open-sourcePhoenix free; AX from $50/mo; Enterprise $50k–100k/yr
Setup time60 seconds, one config lineMinutes to hours depending on deployment

Decision Guide

Which one fits your stack?

When to choose Iris

  • You're building with MCP-compatible agents (Claude Desktop, Cursor, Windsurf)
  • You want zero-code integration — no SDK imports, no OpenTelemetry setup
  • You want simple self-hosting — one binary, one SQLite file
  • You want fully permissive MIT licensing (not Elastic License 2.0)
  • You need lightweight, focused MCP agent observability without enterprise complexity

When to choose Arize AI

  • You need advanced embedding drift detection across NLP, CV, or multi-modal models
  • You need LLM-as-Judge evaluation with agent eval templates
  • You need enterprise compliance and RBAC today
  • You're using non-MCP frameworks and need broad OpenTelemetry-based instrumentation
  • You need a full Prompt IDE with versioning and automated optimization
  • You're monitoring traditional ML models alongside LLM applications

Last verified: March 2026. This comparison is based on publicly available documentation and may not reflect recent changes to Arize. We aim to keep this page accurate and fair.

See something outdated or incorrect? Report an inaccuracy — we review and update within 48 hours.

Ready to see what your agents are doing?

Add Iris to your MCP config. First trace in 60 seconds. No SDK, no signup, no infrastructure.

Try IrisJoin Cloud Waitlist