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 u14app · MCP Server · ★ 4.7k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is deep-research safe to install? View the security audit →
Deep Research [](http
| Stars | 4,689 |
| Forks | 1,062 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70.1414909976377/100 |
| Open Issues | 40 |
| Last Updated | 2026-06-18 |
| Created | 2025-02-22 |
| Platforms | gemini, mcp, node |
| Est. Tokens | ~17k |
Looking for a deep-research alternative? If you're comparing deep-research 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.
✨ AI Coding, Vim Style
The pretty much "official" DSPy framework for Typescript
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Ollama, Grok, DeepSeek, Perplexity, chat, agents
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, .
AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
Explore other popular mcp server tools:
deep-research is Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.. It is categorized as a MCP Server with 4.7k GitHub stars.
deep-research is primarily written in JavaScript. It covers topics such as anthropic, deep-research, deep-research-api.
You can find installation instructions and usage details in the deep-research GitHub repository at github.com/u14app/deep-research. The project has 4.7k stars and 1062 forks, indicating an active community.
deep-research is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to deep-research on Agent Skills Hub include codecompanion.nvim, ax, py-gpt. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: