by softspark · MCP Server · ★ 180
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ai-toolkit safe to install? View the security audit →
ai-toolkit Professional-grade AI coding toolkit with multi-platform support. Machine-enforced safety, 99 skills, 44 agents, expanded lifecycle hooks, persona presets, experimental opt-in plugin packs, and benchmark tooling — works with Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Google Antigravity, Codex CLI, and opencode, ready in 60 seconds. What's New in v2.8.0 SARIF + permissions audit — emits SARIF 2.1.0 for GitHub Advanced Security Code Scanning; prints per-skill tool usage (e.g. "50 skills use Bash") and flags broad Bash+Write+Edit access. Signed npm provenance — the publish workflow now runs with ; published tarballs carry a cryptographic build-origin attestation verifiable via . Checksum-pinned URL sources — now persists of every URL-sourced rule/hook and warns on upstream content change. turns mismatches into a hard CI failure.
npm install -g @softspark/ai-toolkit
npx @softspark/ai-toolkit installTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: spawns subprocesses. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 180 |
| Forks | 21 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 70.9868949060839/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-15 |
| Created | 2026-03-26 |
| Platforms | claude-code, cli, codex, gemini, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with ai-toolkit for enhanced workflows:
Looking for a ai-toolkit alternative? If you're comparing ai-toolkit 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.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman coll
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Adnify—A lightweight, highly customizable AI Agent Editor.It delivers a superior experience beyond mainstream
Explore other popular mcp server tools:
ai-toolkit is Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).. It is categorized as a MCP Server with 180 GitHub stars.
ai-toolkit is primarily written in Python. It covers topics such as ai-agents, ai-skills, anthropic.
The README on GitHub (github.com/softspark/ai-toolkit) gives: npm install -g @softspark/ai-toolkit , then npx @softspark/ai-toolkit install. Usage details are in the same README.
ai-toolkit is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to ai-toolkit on Agent Skills Hub include memorix, Overture, agnix. 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: