# Cordon

> Use this tool when you need to enforce governance and compliance policies between AI agents and servers, or require granular control over tool access and approval workflows. Cordon intercepts tool calls to apply allow/block/approve policies and maintains immutable audit logs, supporting human-in-the-loop approval via terminal or Slack. It provides a secure interface for managing AI agent interactions with databases and APIs, ensuring restricted access and preventing unauthorized actions.

Canonical page: https://skillsregistry.net/skills/cordon  
JSON: https://api.skillsregistry.net/v1/skills/cordon

## Description

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.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cordon)
- **Repository:** <https://github.com/marras0914/cordon>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cordon"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cordon` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cordon/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt