reins MCP Server
pegasi-ai/reins
[](https://agentrank-ai.com/tool/pegasi-ai--reins/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Stop AI agents from doing things you didn't ask for.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
pegasi-ai/reins is a Python tool licensed under Apache-2.0. Stop AI agents from doing things you didn't ask for. Topics: agent-security, ai-safety, audit-trail, browser-automation, cua, human-in-the-loop, intervention, agent-observability, ai-monitoring, mcp, claude-code-skill, openclaw-security, claude-code-marketplace, claude-code-plugin.
Ranked #3884 out of 24846 indexed tools.
Ecosystem
Score Breakdown
392 stars → growing community
Last commit 1mo ago → moderate activity
10/31 issues closed → many open issues
6 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/pegasi-ai--reins/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/pegasi-ai--reins/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/pegasi-ai--reins" alt="AgentRank"></a> Matched Queries
From the README
<div align="center">
<h1>🪢 Reins</h1>
<p><strong>Security controls for AI agents.</strong></p>
<p>
<a href="https://github.com/pegasi-ai/reins">github.com/pegasi-ai/reins</a>
</p>
<p>
<a href="https://www.npmjs.com/package/clawreins"></a>
<a href="https://www.npmjs.com/package/clawreins"></a>
<a href="https://www.apache.org/licenses/LICENSE-2.0"></a>
<a href="http://www.typescriptlang.org/"></a>
= 18.0.0">
</p>
</div>
> 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 @ Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.