by mlhher · MCP Server · ★ 455
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 455 |
| Forks | 50 |
| Language | Go |
| Category | MCP Server |
| Quality Score | 63/100 |
| Open Issues | 17 |
| Last Updated | 2026-11-02 |
| Created | 2026-02-22 |
| Platforms | claude-code, cli, go, mcp |
| Est. Tokens | ~19k |
Late English | 简体中文 The AI agent that always stays sharp. 64k context window. 200k+ tokens of work. Late isolates execution steps to keep your model's context clean during long workflows. Drop it into any project. Works with any cloud provider or local model.
These tools work well together with late-cli for enhanced workflows:
Looking for a late-cli alternative? If you're comparing late-cli 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.
A local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods whil
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode
🤖 Automatically collected AI repos, tools, websites, papers & tutorials. 实用AI百宝箱 💎
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: