by pegasi-ai · MCP Server · ★ 383
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🪢 Reins Security controls for AI agents. github.com/pegasi-ai/reins = 18.0.0" In Greek myth, Athena gave Bellerophon the golden bridle — reins included — that let him guide Pegasus. Reins applies the same idea to AI agents: raw power is not enough — what matters is making it controllable. Reins enforces deterministic security policies on every agent action, scans your configs for OWASP ASI10 vulnerabilities, and tracks drift over time. Policies evaluate in under 50ms. Works with Claude Code PreToolUse and PostToolUse hooks, OpenClaw, and any MCP-compatible agent. Quickstart bash npm install -g @pegasi-ai/reins reins init
| Stars | 383 |
| Forks | 49 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 63.8952630746041/100 |
| Open Issues | 11 |
| Last Updated | 2026-04-21 |
| Created | 2023-04-13 |
| Platforms | browser, mcp, python |
| Est. Tokens | ~14061k |
These tools work well together with reins for enhanced workflows:
Looking for a reins alternative? If you're comparing reins 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.
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch.
An open-source agentic LLM gateway & router that cost-optimize your agentic workflows in your way. works with
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interp
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into th
The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in co
Explore other popular mcp server tools:
reins is Runtime security for OpenClaw agents. Scan, fix, monitor.. It is categorized as a MCP Server with 383 GitHub stars.
reins is primarily written in Python. It covers topics such as agent-observability, agent-security, ai-monitoring.
You can find installation instructions and usage details in the reins GitHub repository at github.com/pegasi-ai/reins. The project has 383 stars and 49 forks, indicating an active community.
reins is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to reins on Agent Skills Hub include Aegis, bitrouter, template-repo. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.