# Trent

This MCP server reviews code, plans, and configs, models threats across a repo or website, and tracks fixes when security work continues.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9
- Author: trnt-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/trnt-ai/trent-agent-plugin
- Updated: 2026-10-02
- HTML: https://affpapa.org/en/nevibecode/mcp/trent

## What it does

Trent adds an AI security engineer to your coding agent through MCP. It can review a diff, plan, or configuration, scan a repository or website, and show the findings it receives. Its skills route these requests through `trent-security-advisor`, `trent-threats`, or `trent-repo`.

The `/trent:trent-loop` command works on a new branch, checks each change with your tests and Trent’s security advisor, then opens one pull request for review. Run it again after merging to rescan the merged code and continue with the remaining findings. Sign-in happens in a browser when a tool is used for the first time, so there is no API key to paste. The first tool call requires that browser sign-in.

## Requirements
- Remote server: `https://mcp.trent.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http trent https://mcp.trent.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add trent --url https://mcp.trent.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "trent": {
            "url": "https://mcp.trent.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "trent": {
            "type": "http",
            "url": "https://mcp.trent.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http trent https://mcp.trent.ai/mcp
```

## When to use it
- review a diff, plan, or config for security issues
- model threats across a repository
- scan a website and inspect its findings
- apply fixes on a new branch and open a pull request
- check which fixes count after a merge

## Example prompts
- Review this diff for security issues with Trent.
- Build a threat model for this repository and show the findings.
- Run `/trent:trent-loop 3` and fix at most three findings.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [mcp](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — MCP server · ★ 12109
- [Robin: AI-Powered Dark Web OSINT](https://affpapa.org/en/nevibecode/mcp/robin-ai-powered-dark-web-osint.md) — MCP server · ★ 7658
- [jshookmcp](https://affpapa.org/en/nevibecode/mcp/jshookmcp.md) — MCP server · ★ 2061
- [OpenOSINT](https://affpapa.org/en/nevibecode/mcp/openosint.md) — MCP server · ★ 1802

---
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