k-dense-byok — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 K-Dense-AI · MCP Server · ★ 1.2k

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

🔒 Is k-dense-byok safe to install? View the security audit →

About k-dense-byok

K-Dense BYOK Your own AI research assistant, running on your computer, powered by your API keys. K-Dense BYOK (Bring Your Own Keys) is a free, open-source app that gives you an AI research assistant called Kady. Ask Kady a question or give it a task, and it figures out the best way to handle it - sometimes answering directly, sometimes spinning up specialized AI "experts" that work behind the scenes to get you a thorough result. It is built for scientists, analysts, and curious people who want a powerful AI workspace without being locked into a single provider. [![Watch the video](https://img.youtube.com/vi/BVG50

agentic-aiai-agentai-assistantbioinformaticsbyokdrug-discoverygoogle-adklitellmlocal-firstmcp

Quick Facts

Stars1,202
Forks151
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score66.1539108905234/100
Open Issues7
Last Updated2026-09-11
Created2026-03-19
Platformsclaude-code, mcp, node, python
Est. Tokens~16k

Compatible Skills

These tools work well together with k-dense-byok for enhanced workflows:

  • PhD-Zero — semantic(0.44)+complementary+similar_pop+shared_platform (50%)
  • claude-prism — semantic(0.36)+complementary+same_lang+shared_platform (48%)

k-dense-byok alternative? Top 6 similar tools

Looking for a k-dense-byok alternative? If you're comparing k-dense-byok 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.

  • ScienceClaw by AgentTeam-TaichuAI · ⭐ 635

    ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, a

  • sdk-python by strands-agents · ⭐ 6.0k

    A model-driven approach to building AI agents in just a few lines of code.

  • tools by strands-agents · ⭐ 1.3k

    A set of tools that gives agents powerful capabilities.

  • samples by strands-agents · ⭐ 852

    Agent samples built using the Strands Agents SDK.

  • comfyui-mcp by artokun · ⭐ 745

    Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video

  • agent-builder by strands-agents · ⭐ 424

    An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is k-dense-byok?

k-dense-byok is An AI co-scientist running on your desktop. Claude Science but better.. It is categorized as a MCP Server with 1.2k GitHub stars.

What programming language is k-dense-byok written in?

k-dense-byok is primarily written in TypeScript. It covers topics such as agentic-ai, ai-agent, ai-assistant.

How do I install or use k-dense-byok?

You can find installation instructions and usage details in the k-dense-byok GitHub repository at github.com/K-Dense-AI/k-dense-byok. The project has 1.2k stars and 151 forks, indicating an active community.

What license does k-dense-byok use?

k-dense-byok is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to k-dense-byok?

The top alternatives to k-dense-byok on Agent Skills Hub include ScienceClaw, sdk-python, tools. 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