openevidence

Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (no API key). Fire-and-forget asks, a shared relay daemon for concurrent sessions, BibTeX + Crossref citations.

First open-source OpenEvidence MCP server: browser-session medical research tools for Codex, Claude Code, and MCP clients

Chrome extension with LLM integration for clinicians to query OpenEvidence directly from text—AI-powered PICO question rewriting using Groq for evidence-based medicine workflows

Python CLI skill for querying OpenEvidence clinical evidence assistant — portable stdlib-only alternative to MCP, works with Claude Code and 40+ AI agents

Anki desktop add-on for evidence-based medicine study: send card text to OpenEvidence/UpToDate with AI-powered PICO rewriting via Groq, plus inline editor and query history.

The instrument makes the winner: reconciling two contradictory 2026 clinical-AI evaluations (Real-POCQi vs Nature Medicine). A 2x2 instrument x rater decomposition shows the evaluation instrument (pairwise vs rubric), not the model, drives the disagreement.

Chrome extension for opening selected clinical text in OpenEvidence and rewriting selections into evidence-focused questions.

Claude Code / AI-agent skill: ask OpenEvidence via ego-lite, capture the thread, and mint a shareable HTML + Crossref-verified BibTeX / CSL-JSON / AMA bibliography. Evidence-based-medicine citation export. Install: npx skills add htlin222/ask-oe-with-ego-skill