{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4sb8q2733p8j","handle":"orpheus-mcp","url":"https://wellknown.network/agents/orpheus-mcp","links":{"self":"https://wellknown.network/agents/orpheus-mcp/record.json","html":"https://wellknown.network/agents/orpheus-mcp","markdown":"https://wellknown.network/agents/orpheus-mcp/record.md","api":"https://wellknown.network/api/v1/agents/orpheus-mcp","status":"https://wellknown.network/api/v1/agents/orpheus-mcp/status","claim":"https://wellknown.network/agents/orpheus-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/orpheus-mcp/claim.json","badge":"https://wellknown.network/agents/orpheus-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/orpheus-mcp/history","tools":"https://wellknown.network/api/v1/agents/orpheus-mcp/tools"},"ard":{"identifier":"urn:air::server:orpheus-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"orpheus-mcp","summary":"Visual UI snip tool for A/B variant generation — drag to select a component, get design variants instantly","description":"<p align=\"center\">\n  <img src=\"images/orpheus_logo.png\" alt=\"Orpheus Logo\" width=\"200\">\n</p>\n\n# Orpheus — Technical Design Document\n\n**Version:** 1.0\n**Date:** 2026-03-19\n**Status:** Draft\n\n---\n\n## Table of Contents\n\n1. Executive Summary\n2. Problem Statement\n3. System Overview\n4. Component Design\n5. Data Models\n6. Retrieval Pipeline\n7. Learning-to-Rank System\n8. Attribution System\n9. Human-in-the-Loop Flow\n10. Multi-Metric Ingestion\n11. Corpus Design\n12. Corpus Quality Validation\n13. Corpus Improvement Loops\n14. Integration Architecture (PostHog, GA4)\n15. Limitations and Known Tradeoffs\n16. React SDK Expansion Plan\n17. One-Week MVP\n18. 4-Week Build Plan (Compressed Rollout)\n19. Project Structure\n\n---\n\n## 1. Executive Summary\n\nDesign decisions in UI/UX work are currently made through a combination of intuition, tribal knowledge, and periodic A/B testing — but these three information sources rarely talk to each other. A designer proposes a variant, engineers run the test, results go into a spreadsheet, and the next designer starts from scratch. The A/B UI Variant Recommender closes this loop: it generates design variants informed by what has actually worked, improves from every test result and user selection it observes, and always explains exactly why it proposed what it proposed.\n\nThe system operates as an MCP (Model Context Protocol) server, integrating directly into AI coding tools like Claude Code, Cursor, and Windsurf. When a developer or designer asks for UI variants for a hero section, pricing table, or CTA button, the system retrieves the top candidates per domain from a curated corpus (style, color, typography, layout, UX patterns), anchors Variant 1 on the `ui-reasoning.csv` expert recommendation for that product/page context, then selects Variants 2 and 3 by maximizing embedding distance from already-chosen docs — guaranteeing visual diversity without pigeonholing into pre-defined strategy buckets. Strategy labels (e.g. \"bold\", \"layered\") are assigned pos…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["a/b","testing","design","mcp","playwright","ui"],"pricing":null,"endpoints":[{"url":"pypi:orpheus-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"code.testing","name":"Testing","confidence":1,"provenance":"declared"},{"slug":"media.3d","name":"3D & Design","confidence":1,"provenance":"declared"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"declared"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.802,"provenance":"derived"}],"categories":["code","documents","infra","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"orpheus-mcp","registry":"pypi","observedAt":"2026-11-03T21:28:18.508Z","publishedAt":"2026-04-07T23:53:25.369977Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"orpheus-mcp","url":"https://pypi.org/project/orpheus-mcp/","firstSeenAt":"2026-09-10T09:25:00.832Z","fetchedAt":"2026-11-03T21:26:51.505Z","normalizedAt":"2026-11-03T21:26:51.505Z"}]},"firstSeenAt":"2026-09-10T09:25:00.832Z","updatedAt":"2026-11-03T21:28:18.508Z"}