Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add agent-security-scanner -- npx -y agent-security-scanner-mcp~/.codex/config.toml
[mcp_servers.agent-security-scanner]
command = "npx"
args = ["-y", "agent-security-scanner-mcp"]
# codex mcp add agent-security-scanner -- npx -y agent-security-scanner-mcp~/.cursor/mcp.json
{
"mcpServers": {
"agent-security-scanner": {
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"agent-security-scanner": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"agent-security-scanner": {
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"agent-security-scanner": {
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"agent-security-scanner": {
"command": "npx",
"args": [
"-y",
"agent-security-scanner-mcp"
]
}
}
}