claude mcp add gentafe-tooltrust-scanner -- npx -y tooltrust-mcp
{
"mcpServers": {
"gentafe-tooltrust-scanner": {
"command": "npx",
"args": ["-y", "tooltrust-mcp"]
}
}
}
{
"mcpServers": {
"gentafe-tooltrust-scanner": {
"command": "npx",
"args": ["-y", "tooltrust-mcp"]
}
}
}
{
"mcpServers": {
"gentafe-tooltrust-scanner": {
"command": "npx",
"args": ["-y", "tooltrust-mcp"]
}
}
}
About This MCP Server
The tooltrust-scanner is a developer tool that scans Model Context Protocol servers for potential security vulnerabilities, including prompt injection, data exfiltration, and privilege escalation, and is accessible via npm and stdio. It is part of the AgentSafe-AI project and is packaged as tooltrust-mcp. Developers would use this tool to identify and address security risks in their MCP servers, ensuring the integrity of their AI systems.
Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with developer tools capabilities via the stdio transport.
Package
tooltrust-mcp on npm
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on npm.
What tools does it provide?
The ToolTrust Scanner server extends your AI assistant with developer tools capabilities. Once installed, your AI can use its tools automatically.
