by kagan-sh · MCP Server · ★ 108
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
The Orchestration Layer for AI Coding Agents
| Stars | 108 |
| Forks | 8 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 55.0341650787553/100 |
| Open Issues | 5 |
| Last Updated | 2026-07-07 |
| Created | 2026-01-25 |
| Platforms | claude-code, cli, codex, gemini, mcp, python |
| Est. Tokens | ~13k |
These tools work well together with kagan-legacy for enhanced workflows:
Looking for a kagan-legacy alternative? If you're comparing kagan-legacy 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.
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Terminal task manager with intelligent schedule optimization.Keyboard-only. No dragging, no micromanagement.
TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman coll
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Explore other popular mcp server tools:
kagan-legacy is The Orchestration Layer for AI Coding Agents. It is categorized as a MCP Server with 108 GitHub stars.
kagan-legacy is primarily written in Python. It covers topics such as ai, ai-agents, antrophic.
You can find installation instructions and usage details in the kagan-legacy GitHub repository at github.com/kagan-sh/kagan-legacy. The project has 108 stars and 8 forks, indicating an active community.
kagan-legacy is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kagan-legacy on Agent Skills Hub include agnix, taskdog, bridle. 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: