🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 55 rules for prompt injection, credential exposure, SSRF & tool poisoning. pip install mcp-safeguard
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-safeguard": {
"command": "uvx",
"args": [
"mcp-safeguard"
]
}
}
}
Run in terminal:
claude mcp add mcp-safeguard uvx mcp-safeguard
Add to .cursor/mcp.json:
{
"mcpServers": {
"mcp-safeguard": {
"command": "uvx",
"args": [
"mcp-safeguard"
]
}
}
}
Or install with pip: pip install mcp-safeguard
README Excerpt
<div align="center"> **The security scanner for MCP servers.** Detect prompt injection · credential leaks · exposed endpoints · tool poisoning ```bash pip install mcp-safeguard mcp-safeguard scan your-config.json ``` </div> --- ```bash pip install mcp-safeguard git clone https://github.com/SyedAnas01/mcp-safeguard && cd mcp-safeguard
Tools (7)
check_auth_configcheck_endpoint_exposurecompare_scansgenerate_security_reportget_scan_historyscan_mcp_serverscan_tool_definitions
Topics
agentic-aiai-securityclaudeclicursorcybersecuritydevopsllmllm-securitymcpmodel-context-protocolopenaiprompt-injectionpythonsast