by goat-si · MCP Server · ★ 160
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: install step in a code block runs a script from an untrusted host. Scanned against 44 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 | 160 |
| Forks | 20 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 68/100 |
| Open Issues | 99 |
| Last Updated | 2026-11-20 |
| Created | 2026-10-10 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~16k |
Install · Downloads · User guides · How it is built GOAT runs the coding agents you already use, such as Claude Code, Codex and Cursor, on the machines you own: your laptop, a desktop at home, an SSH server or a cloud machine. You steer all of them from one place, whether that is the desktop app, a browser or your phone.
Looking for a goat alternative? If you're comparing goat 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.
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
An LLM council that reviews your coding agent's every move
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: