linkly-ai-skills — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

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 LinklyAI · MCP Server · ★ 59

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

🔒 Is linkly-ai-skills safe to install? View the security audit →

About linkly-ai-skills

Linkly AI Skills Agent Skills for Linkly AI — search, browse, and read your local documents (and linked cloud libraries) from any AI coding agent. This skill teaches AI agents how to use Linkly AI's document search capabilities, enabling them to find and read your locally indexed documents (PDF, Markdown, DOCX, PPTX, TXT, HTML, and more) as well as cloud libraries you've linked via Linkly Web. What is Linkly AI? Linkly AI is a desktop application that indexes documents on your computer and provides full-text search, structural outlines, and content reading through a local MCP server. Through the cloud gateway it can also reach cloud libraries you've linked via Linkly Web. Think of it as a knowledge base — local and cloud — that AI agents can query. What Does This Skill Do? When installed, this skill enables AI agents to: Search your local documents (and linked cloud libraries) by keywords with relevance ranking, time windows, and path filters Find paths for fuzzy or cross-language container names ("in my WeChat", "在 Notion 笔记里") by matching against the indexed file paths Explore the knowledge base for an overview of themes, document types,

agent-toolsai-searchknowledge-baselocal-firstmcpmemory-managementresearch-toolskills

Quick Facts

Stars59
Forks4
LanguageShell
CategoryMCP Server
LicenseApache-2.0
Quality Score73.7028979407712/100
Open Issues4
Last Updated2026-09-16
Created2026-03-03
Platformscli, mcp
Est. Tokens~12k

linkly-ai-skills alternative? Top 6 similar tools

Looking for a linkly-ai-skills alternative? If you're comparing linkly-ai-skills 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.

  • gno by gmickel · ⭐ 109

    Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP

  • OpenDocuments by joungminsung · ⭐ 103

    Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sour

  • human-mcp by mrgoonie · ⭐ 294

    Bringing Human Capabilities to AI Agents

  • ATaC by ATaC-team · ⭐ 291

    Record and Replay AI Agent Trajectories.

  • gram by speakeasy-api · ⭐ 270

    Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute ag

  • langchainjs-mcp-adapters by langchain-ai · ⭐ 247

    ** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters **

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is linkly-ai-skills?

linkly-ai-skills is Agent Skills for Linkly AI — search, browse, and read your local documents from any AI coding agent.. It is categorized as a MCP Server with 59 GitHub stars.

What programming language is linkly-ai-skills written in?

linkly-ai-skills is primarily written in Shell. It covers topics such as agent-tools, ai-search, knowledge-base.

How do I install or use linkly-ai-skills?

You can find installation instructions and usage details in the linkly-ai-skills GitHub repository at github.com/LinklyAI/linkly-ai-skills. The project has 59 stars and 4 forks, indicating an active community.

What license does linkly-ai-skills use?

linkly-ai-skills 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 linkly-ai-skills?

The top alternatives to linkly-ai-skills on Agent Skills Hub include gno, OpenDocuments, human-mcp. 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