# aegis

> Use this tool when you need to audit AI agent permissions and access, as it scans for credentials, injection, and reach to identify potential security vulnerabilities without requiring heavy infrastructure. Aegis provides a lightweight MCP server solution for monitoring and controlling AI agent activity, helping to prevent unauthorized access and data breaches. Ideal for use cases where security and compliance are critical, such as in sensitive data environments or high-risk applications.

Canonical page: https://skillsregistry.net/skills/cognis-digital-aegis  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-aegis

## Description

MCP server for auditing AI agent permissions and access by scanning for the trifecta of credentials, injection, and reach without heavy infrastructure.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/myl9fkoxtl)
- **Repository:** <https://github.com/cognis-digital/aegis>

## 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": "cognis-digital-aegis"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-aegis` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-aegis/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