Description

ToolTrust Scanner analyzes MCP server tool definitions to detect security risks including prompt injection, unauthorized data exfiltration, and privilege escalation patterns. It integrates directly into the MCP client workflow to evaluate server trustworthiness before tools are invoked. Results include actionable risk scores and specific vulnerability findings.

🔬 Playground

Try ToolTrust Scanner live in the browser with security context.
⚪
Unverified
No automated security scan has been run on this server yet.

Installation 

git clone https://github.com/agentsafe-ai/tooltrust-scanner

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json 
{
  "mcpServers": {
    "tooltrust-scanner": {
      "command": "node",
      "args": [
        "path/to/server.js"
      ]
    }
  }
}

Community Reviews

Authenticated reviews from GitHub users. No anonymous submissions. Your experience helps others choose wisely.

—
★★★★★
0 reviews
5★
0
4★
0
3★
0
2★
0
1★
0

No reviews yet. Be the first to share your experience.