by Keesan12 · MCP Server · ★ 394
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx -y martin-loop@latest start
npx -y martin-loop@latest demoTaken from the project's README on GitHub.
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 | 394 |
| Forks | 62 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 70/100 |
| Open Issues | 1 |
| Last Updated | 2026-11-03 |
| Created | 2026-04-04 |
| Platforms | claude-code, codex, mcp, node |
| Est. Tokens | ~18k |
MartinLoop MartinLoop gives AI coding agents budgets, stop conditions, rollback rules, and receipts. Built from thousands of agent runs where the problem was not intelligence -- it was uncontrolled execution. Get started: Try the demo: MartinLoop is part of the NVIDIA Inception program. Why MartinLoop AI coding agents are useful, but unbounded retry loops are e
These tools work well together with martin-loop for enhanced workflows:
Looking for a martin-loop alternative? If you're comparing martin-loop 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 action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands,
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interp
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Remote approvals, policy checks, and execution evidence for unattended AI agents.
Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C
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: