smart-connections-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 msdanyg · MCP Server · ★ 54

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

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

About smart-connections-mcp

Smart Connections MCP Server Give Claude semantic memory of your Obsidian vault. A Model Context Protocol (MCP) server that lets Claude search your notes by meaning, map how ideas connect, and pull the right context on demand — reusing the embeddings the Smart Connections plugin already generated, so there's nothing new to index. Keyword search finds the notes that share your words. This finds the notes that share your ideas — the ones you forgot you wrote. If it earns a spot in your workflow, ⭐ star it so other Obsidian users find it. Why use it Your vault already holds the answer — the problem is retrieval. Claude can't grep its way to "the note where I reasoned about pricing," because you phrased it three different ways across six months. This server hands Claude the same 384-dimensional semantic index Smart Connections built inside Obsidian, so "find notes similar to my pricing t

anthropicclaudeclaude-desktopembeddingsknowledge-graphmcpmcp-servermodel-context-protocolnote-takingobsidian

Quick Facts

Stars54
Forks15
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score71.550091257404/100
Last Updated2026-08-22
Created2025-10-13
Platformsclaude-code, mcp, node
Est. Tokens~12k

smart-connections-mcp alternative? Top 6 similar tools

Looking for a smart-connections-mcp alternative? If you're comparing smart-connections-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.

  • notion-mcp-server by awkoy · ⭐ 172

    Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context

  • gno by gmickel · ⭐ 115

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

  • ChatCrystal by ZengLiangYi · ⭐ 58

    Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search,

  • omega-memory by omega-memory · ⭐ 219

    Persistent memory for AI coding agents

  • mengram by alibaizhanov · ⭐ 195

    Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn fro

  • claude-historian-mcp by Vvkmnn · ⭐ 178

    📜 An MCP server for conversation history search and retrieval in Claude Code

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is smart-connections-mcp?

smart-connections-mcp is Give Claude semantic memory of your Obsidian vault — local semantic search over Smart Connections embeddings via MCP. Multi-vault, block-level, 100% private.. It is categorized as a MCP Server with 54 GitHub stars.

What programming language is smart-connections-mcp written in?

smart-connections-mcp is primarily written in TypeScript. It covers topics such as anthropic, claude, claude-desktop.

How do I install or use smart-connections-mcp?

You can find installation instructions and usage details in the smart-connections-mcp GitHub repository at github.com/msdanyg/smart-connections-mcp. The project has 54 stars and 15 forks, indicating an active community.

What license does smart-connections-mcp use?

smart-connections-mcp is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to smart-connections-mcp?

The top alternatives to smart-connections-mcp on Agent Skills Hub include notion-mcp-server, gno, ChatCrystal. 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