# Code Sentinel

Code Sentinel detects security flaws, deceptive logic, and stubbed code using a remote HTTP endpoint.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 850 installs
- Author: salrad
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/salrad/code-sentinel
- Updated: 2026-01-03
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/code-sentinel

## What it does

The server operates over HTTP at `https://code-sentinel--salrad.run.tools` without local setup. Your assistant dispatches inspection tasks to dedicated functions.

Inspection tools target specific quality aspects. Tool `check_security` checks for hardcoded tokens, SQL injection, and XSS. Functions `check_deceptive_patterns` and `check_placeholders` uncover empty catch blocks, suppressed errors, and leftover TODO comments. Architectural reviews rely on `analyze_design_patterns`, which identifies Gang of Four structures like Singleton or Strategy.

Output arrives as structured data or a visual HTML report via `generate_report`. Because this runs via HTTP, examined files travel to an external service.

## Requirements
- Remote server: `https://code-sentinel--salrad.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http code-sentinel https://code-sentinel--salrad.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add code-sentinel --url https://code-sentinel--salrad.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "code-sentinel": {
            "url": "https://code-sentinel--salrad.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "code-sentinel": {
            "type": "http",
            "url": "https://code-sentinel--salrad.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http code-sentinel https://code-sentinel--salrad.run.tools
```

## When to use it
- locate hardcoded secrets, XSS, and SQL injection flaws
- catch silent failures and empty catch statements
- flag unfinished logic and lingering TODO markers
- identify GoF design patterns across modules
- export review findings into an HTML report

## Example prompts
- Run `check_security` on `auth.py` to identify leaked keys.
- Scan `src/api` with `check_placeholders` to list leftover TODO items.
- Call `generate_report` to build an HTML summary for `payment.ts`.

## Similar
- [sentinel](https://affpapa.org/en/nevibecode/skills/sentinel.md) — skill · 106 installs
- [WG Code Sentinel](https://affpapa.org/en/nevibecode/agents/wg-code-sentinel.md) — subagent · ★ 41430 repo stars
- [HefestoAI](https://affpapa.org/en/nevibecode/mcp/artvepa80-hefestoai.md) — MCP server · 1241 installs
- [code-reviewer](https://affpapa.org/en/nevibecode/agents/voltagent-community-code-reviewer.md) — subagent · 31050 installs
- [audit-prep-assistant](https://affpapa.org/en/nevibecode/skills/audit-prep-assistant.md) — skill · 6300 installs
- [code-review-pro](https://affpapa.org/en/nevibecode/skills/code-review-pro.md) — skill · 2600 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
