← Back to leaderboard
/100
Unscored ○ Unscored 00

arai

Policy enforcement for AI coding agents derived from existing instruction files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md) — no separate YAML to maintain. Rules with prohibitive predicates (`never`, `forbids`, `must_not`) emit `permissionDecision: deny` to block tool calls in Claude Code; advisory rules inject context. PostToolUse is correlated with PreToolUse to produce per-rule obeyed/ignored compliance verdicts in a local JSONL audit log. MCP tools — `arai_add_guard` (register rules mid-session), `arai_list_guards`, `arai_recent_decisions` — work in any MCP client (Claude Desktop, Cursor, Windsurf, Cline). No network on the hook hot path; opt-out anonymous telemetry.

Anthropic GitHub
Unscored visibility — 0/0 applicable dimensions scored
○ Schema Quality — Protocol — Reliability ○ Docs & Maintenance ○ Security Hygiene — Schema Interpretability
Schema Quality
42% weight
Protocol Compliance
N/A
Local server
Reliability
N/A
Local server
Docs & Maintenance
25% weight
Security Hygiene
33% weight
30-Day Trend
Embed Badge

Add this to your README to display your MCP Scoreboard grade:

MCP Score Badge
[![MCP Score](https://mcpscoreboard.com/badge/93c709f9-15f7-4ca9-8f5b-c2346888a5d8.svg)](https://mcpscoreboard.com/server/93c709f9-15f7-4ca9-8f5b-c2346888a5d8/)