René's URL Explorer Experiment


Title: Iris — stop shipping agents on vibes

Open Graph Title: Iris — stop shipping agents on vibes

X Title: Iris — stop shipping agents on vibes

Description: Stop shipping agents on vibes. Score output quality, detect PII and injection attacks, enforce cost thresholds across all your agents. Open-source core, self-hosted, one command to start.

Open Graph Description: Score output quality, catch safety failures, enforce cost budgets across every MCP agent. Open-source core.

X Description: Score your agents. Catch PII leaks, hallucinations, and cost overruns before users do. Open-source MCP server.

Mail addresses
hello@iris-eval.com
hello@iris-eval.com

Opengraph URL: https://iris-eval.com

X: @iris_eval

direct link

Domain: iris-eval.com

Hey, it has json ld scripts: 
{"@context":"https://schema.org","@type":"Organization","name":"Iris","url":"https://iris-eval.com","logo":"https://iris-eval.com/iris-logo.svg","sameAs":["https://github.com/iris-eval/mcp-server","https://x.com/iris_eval"]}
 
{"@context":"https://schema.org","@type":"SoftwareApplication","name":"Iris","applicationCategory":"DeveloperApplication","operatingSystem":"Any","downloadUrl":"https://www.npmjs.com/package/@iris-eval/mcp-server","softwareVersion":"0.21.0","applicationSubCategory":"AI Agent Evaluation","url":"https://iris-eval.com","description":"Stop shipping agents on vibes. Score output quality, catch safety failures, enforce cost budgets across all your agents.","offers":{"@type":"Offer","price":"0","priceCurrency":"USD"}}
og:site_nameIris
og:imagehttps://iris-eval.com/og-social-preview.png?v=4
og:typewebsite
twitter:cardsummary_large_image
twitter:imagehttps://iris-eval.com/og-social-preview.png?v=4

Links:

v0.21.0A security release: what an agent or a client sends Iris is bounded before Iris reads it, and a tool argument can narrow what the operator allows but never widen it — read the release notes→https://iris-eval.com/releases
Irishttps://iris-eval.com/
Producthttps://iris-eval.com/#product
Playgroundhttps://iris-eval.com/playground
Proofhttps://iris-eval.com/proof
Capabilitieshttps://iris-eval.com/capabilities
Learnhttps://iris-eval.com/learn
Comparehttps://iris-eval.com/compare
Pricinghttps://iris-eval.com/pricing
Bloghttps://iris-eval.com/blog
Open Sourcehttps://iris-eval.com/#open-source
Roadmaphttps://iris-eval.com/#roadmap
GitHubhttps://github.com/iris-eval/mcp-server
Get Startedhttps://iris-eval.com/#open-source
https://glama.ai/mcp/servers/iris-eval/mcp-server
https://cursor.directory/plugins/iris
https://www.npmjs.com/package/@iris-eval/mcp-server
https://github.com/iris-eval/mcp-server
https://github.com/iris-eval/mcp-server/actions
https://github.com/iris-eval/mcp-server/blob/main/LICENSE
Get Startedhttps://iris-eval.com#open-source
Star on GitHubhttps://github.com/iris-eval/mcp-server
Follow @iris_evalhttps://x.com/iris_eval
View on npmhttps://www.npmjs.com/package/@iris-eval/mcp-server
Cursor Directoryhttps://cursor.directory/plugins/iris
every row, with its sourcehttps://iris-eval.com/clients
cursor://anysphere.cursor-deeplink/mcp/install?name=iris-eval&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBpcmlzLWV2YWwvbWNwLXNlcnZlciJdLCJlbnYiOnsiSVJJU19MT0dfTEVWRUwiOiJpbmZvIn19
Get Startedhttps://iris-eval.com#open-source
ComparisonOctober 2026Iris vs Langfuse vs Phoenix vs Promptfoo: where each wins, where each losesFour ways to evaluate an AI agent, read from each vendor's own pages on 2026-10-01: how each gets into your stack, where the evaluation runs, what it costs to run, how it self-hosts, and what it does with MCP.Read posthttps://iris-eval.com/blog/iris-vs-langfuse-vs-phoenix-vs-promptfoo
ReportMarch 2026The State of MCP Agent ObservabilityThe gap between deploying AI agents and understanding what they're doing. Covers protocol-native observability, heuristic vs. semantic eval, cost visibility, and EU AI Act implications.Read reporthttps://iris-eval.com/blog/state-of-mcp-agent-observability-2026
View all postshttps://iris-eval.com/blog
MeasuredEvery rule's precision and recall, publishedEach built-in rule is measured on a public corpus, and the proof check is required on every pull request: a rule change cannot merge without its numbers.https://iris-eval.com/proof
See the capability map →https://iris-eval.com/capabilities
Start buildinghttps://iris-eval.com#open-source
Star on GitHubhttps://github.com/iris-eval/mcp-server
Featureshttps://iris-eval.com/#product
Playgroundhttps://iris-eval.com/playground
Proofhttps://iris-eval.com/proof
Capabilitieshttps://iris-eval.com/capabilities
Pricinghttps://iris-eval.com/pricing
Bloghttps://iris-eval.com/blog
Quick Starthttps://iris-eval.com/#open-source
Roadmaphttps://iris-eval.com/#roadmap
Agent Eval Guidehttps://iris-eval.com/learn/agent-eval
The Eval Taxhttps://iris-eval.com/learn/eval-tax
Eval Drifthttps://iris-eval.com/learn/eval-drift
The Eval Gaphttps://iris-eval.com/learn/eval-gap
Eval Coveragehttps://iris-eval.com/learn/eval-coverage
EDDhttps://iris-eval.com/learn/eval-driven-development
The Eval Loophttps://iris-eval.com/learn/eval-loop
Self-Calibrating Evalhttps://iris-eval.com/learn/self-calibrating-eval
Output Quality Scorehttps://iris-eval.com/learn/output-quality-score
Iris vs Langfusehttps://iris-eval.com/compare/langfuse
Iris vs LangSmithhttps://iris-eval.com/compare/langsmith
Iris vs Heliconehttps://iris-eval.com/compare/helicone
Iris vs Braintrusthttps://iris-eval.com/compare/braintrust
Iris vs Arizehttps://iris-eval.com/compare/arize
Iris vs DeepEvalhttps://iris-eval.com/compare/deepeval
Iris vs Confident AIhttps://iris-eval.com/compare/confident-ai
Iris vs Patronus AIhttps://iris-eval.com/compare/patronus-ai
Iris vs Promptfoohttps://iris-eval.com/compare/promptfoo
Iris vs Galileohttps://iris-eval.com/compare/galileo
Iris vs Opikhttps://iris-eval.com/compare/opik
Iris vs Weavehttps://iris-eval.com/compare/weave
Iris vs Judgment Labshttps://iris-eval.com/compare/judgment
Iris vs Latitudehttps://iris-eval.com/compare/latitude
GitHubhttps://github.com/iris-eval/mcp-server
npmhttps://www.npmjs.com/package/@iris-eval/mcp-server
@iris_evalhttps://x.com/iris_eval
Privacyhttps://iris-eval.com/privacy
Termshttps://iris-eval.com/terms
Securityhttps://iris-eval.com/security

Viewport: width=device-width, initial-scale=1

URLs of crawlers that visited me.