openevidence-mcp — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by htlin222 · MCP Server · ★ 74

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is openevidence-mcp safe to install? View the security audit →

About openevidence-mcp

OpenEvidence MCP (Cookie Auth Fork) Use OpenEvidence from Claude Code, Codex CLI, Gemini CLI, Claude Desktop, Cursor, Cline, Continue, and any MCP-compatible client. <im

academic-toolsbibtexbrowser-extensionclaude-codeclinical-researchcodex-clicrossrefevidence-based-medicinegemini-climcp

Quick Facts

Stars74
Forks15
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score72.4654510149502/100
Last Updated2026-09-14
Created2026-04-08
Platformsbrowser, claude-code, cli, codex, gemini, mcp, node
Est. Tokens~16k

openevidence-mcp alternative? Top 6 similar tools

Looking for a openevidence-mcp alternative? If you're comparing openevidence-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • cli-anything-zotero by PiaoyangGuohai1 · ⭐ 122

    CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, no

  • medsci-skills by Aperivue · ⭐ 325

    Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publ

  • bibverify by Hylouis233 · ⭐ 99

    Cross-platform BibTeX verification for researchers and AI assistants — CLI, Python API, MCP server, and explai

  • AlterLab-Academic-Skills by AlterLab-IEU · ⭐ 71

    242 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data

  • browser-echo by instructa · ⭐ 320

    ⚡ Stream browser logs to terminal, zero setup, perfect for Ai Agents

  • nature-academic-search by wp-a · ⭐ 250

    Academic Paper Search:中文科研用户的 Codex / Claude Code / DeepSeek Harness Skill + MCP;跨 CrossRef、PubMed、arXiv、OpenA

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is openevidence-mcp?

openevidence-mcp is 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. It is categorized as a MCP Server with 74 GitHub stars.

What programming language is openevidence-mcp written in?

openevidence-mcp is primarily written in TypeScript. It covers topics such as academic-tools, bibtex, browser-extension.

How do I install or use openevidence-mcp?

You can find installation instructions and usage details in the openevidence-mcp GitHub repository at github.com/htlin222/openevidence-mcp. The project has 74 stars and 15 forks, indicating an active community.

What license does openevidence-mcp use?

openevidence-mcp is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to openevidence-mcp?

The top alternatives to openevidence-mcp on Agent Skills Hub include cli-anything-zotero, medsci-skills, bibverify. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools