loading…
Search for a command to run...
loading…
Side-by-side comparison of two Model Context Protocol servers. Pick the right one for Claude Desktop, Claude Code, or Cursor.
Policy enforcement for AI coding agents derived from existing instruction files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md) — no
Secure file operations with configurable access controls.
| Feature | taniwhaai/arai | Filesystem |
|---|---|---|
| Pricing | Free | Free |
| Installs | — | 1 |
| Rating | — | — |
| Verified | — | |
| Hosted | — | — |
| Tools | — | — |
| Category | development | development |
| Author | taniwhaai | Community |
| Repo | taniwhaai/arai | modelcontextprotocol/servers |
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, mustnot) 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 — araiaddguard (register rules mid-session), arailistguards, arairecentdecisions — work in any MCP client (Claude Desktop, Cursor, Windsurf, Cline). No network on the hook hot path; opt-out anonymous telemetry.
Secure file operations with configurable access controls.
Looking for something else? Browse all MCPs or check trending this week.