# AISentinel

> AISentinel — kabzhanov-aisentinel. Use this tool when you need to protect AI agents from unauthorized or malicious tool calls at runtime. AISentinel evaluates every tool call against predefined YAML policies, generating audit trails to ensure compliance and security. Ideal for use cases requiring robust access control and auditing, AISentinel takes in tool calls and YAML policies as inputs and produces audit trails as output.

Canonical page: https://skillsregistry.net/skills/kabzhanov-aisentinel  
JSON: https://api.skillsregistry.net/v1/skills/kabzhanov-aisentinel

## Description

An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/u2209jnccb)
- **Repository:** <https://github.com/Kabzhanov/AISentinel>

## 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": "kabzhanov-aisentinel"
    }
  }
}
```

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