# mcp-sentinel

> mcp-sentinel — oktsec-mcp-sentinel. Use this tool when you need to scan MCP servers for security risks and detect potential threats. It solves problems related to exposed tools, destructive operations, and other vulnerabilities by providing a quick scan of the server, taking in server details as input and outputting a report of detected risks. Use mcp-sentinel before trusting an MCP server to ensure its security and integrity.

Canonical page: https://skillsregistry.net/skills/oktsec-mcp-sentinel  
JSON: https://api.skillsregistry.net/v1/skills/oktsec-mcp-sentinel

## Description

Scan MCP servers before you trust them. Detect exposed tools, destructive operations, and security risks in seconds.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** security
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/oktsec/mcp-sentinel)

## 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": "oktsec-mcp-sentinel"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/oktsec-mcp-sentinel` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/oktsec-mcp-sentinel/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