claude mcp add comcognivators-mcp-safeguard -- uvx mcp-safeguard
{
"mcpServers": {
"comcognivators-mcp-safeguard": {
"command": "uvx",
"args": ["mcp-safeguard"]
}
}
}
{
"mcpServers": {
"comcognivators-mcp-safeguard": {
"command": "uvx",
"args": ["mcp-safeguard"]
}
}
}
{
"mcpServers": {
"comcognivators-mcp-safeguard": {
"command": "uvx",
"args": ["mcp-safeguard"]
}
}
}
About This MCP Server
The com.cognivators/mcp-safeguard server is a security scanner for Model Context Protocol servers that detects potential security threats such as prompt injection, credential leaks, server-side request forgery, and tool poisoning. It connects to MCP servers to analyze their security and enables developers to identify and address vulnerabilities. A developer would use this tool to ensure the security and integrity of their MCP server, particularly when deploying it in a production environment or handling sensitive data.
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with other capabilities via the stdio transport.
Package
mcp-safeguard on pypi
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the stdio transport and is available on pypi.
What tools does it provide?
The mcp-safeguard server extends your AI assistant with other capabilities. Once installed, your AI can use its tools automatically.
