# ToolTrust Scanner

Audits MCP tool specifications before your agent executes them. Identifies permission mismatches, code execution risks, and grades servers from A to F.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 19
- Author: AgentSafe-AI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AgentSafe-AI/tooltrust-scanner
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/tooltrust-scanner

## What it does

ToolTrust Scanner checks agent tool definitions against static security rules. It runs directly as a subprocess via stdio. No open network ports are needed. The server inspects MCP configurations, connects to listed endpoints in parallel, and returns a structured risk breakdown.

The scanner catches arbitrary script execution patterns and credential leaks in input schemas. It also compares package metadata with an inventory of compromised libraries. This blacklist runs completely offline. Zero network calls are required for known bad packages.

When a server omits repository links or dependency details, supply-chain analysis flags coverage as incomplete. This limitation leaves blind spots in third-party code. Always inspect unverified tools manually.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add tooltrust-scanner -- npx -y tooltrust-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add tooltrust-scanner -- npx -y tooltrust-mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "tooltrust-scanner": {
            "command": "npx",
            "args": [
                "-y",
                "tooltrust-mcp"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "tooltrust-scanner": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "tooltrust-mcp"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add tooltrust-scanner npx -y tooltrust-mcp
```

## When to use it
- spot arbitrary code execution hooks inside tool definitions
- catch sensitive credential leaks in input schemas
- flag compromised third-party dependencies using offline lists
- detect name spoofing and tool shadowing across MCP servers

## Example prompts
- Run tooltrust_scan_config to audit active MCP servers
- Scan our MCP configuration and display the security grades

## 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