Cordon

Security proxy that enforces granular policies and audit logging for AI agent tool access.

Visit Site GitHub
Category Agents
Added Apr 19, 2026
Views 40

About

Acts as a governance layer between AI agents and MCP servers, intercepting tool calls to enforce allow/block/approve policies per tool or server. Maintains immutable audit logs for compliance, supports human-in-the-loop approval via terminal or Slack, and prevents unrestricted agent access to databases and APIs. Written as a TypeScript monorepo with CLI, SDK, and proxy engine packages.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/cordon.svg)](https://hifriendbot.com/ai-list/cordon/)
Listed on AiList

Compare

Cordon vs Policy Firewall Cordon vs Ubuntu System Control Cordon vs QueryShield

Similar Projects

Policy Firewall

2

Security proxy that enforces allow/deny policies on MCP tool calls between AI clients and downstream MCP servers, with secret redaction and audit logging.

MCP Servers

Ubuntu System Control

29

Provides secure Ubuntu system control with safe file operations, command execution, and system information gathering through configurable security policies, path traversal prevention, command filtering, and comprehensive audit logging.

MCP Servers

QueryShield

Secure SQL proxy for AI agents with natural language to SQL translation, AST safety checks, per-agent row-level security, and audit logging.

Agents

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project