MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add sentinel-scan -- npx -y sentinel-scan-cli~/.codex/config.toml
[mcp_servers.sentinel-scan]
command = "npx"
args = ["-y", "sentinel-scan-cli"]
# codex mcp add sentinel-scan -- npx -y sentinel-scan-cli~/.cursor/mcp.json
{
"mcpServers": {
"sentinel-scan": {
"command": "npx",
"args": [
"-y",
"sentinel-scan-cli"
]
}
}
}.vscode/mcp.json
{
"servers": {
"sentinel-scan": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sentinel-scan-cli"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"sentinel-scan": {
"command": "npx",
"args": [
"-y",
"sentinel-scan-cli"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"sentinel-scan": {
"command": "npx",
"args": [
"-y",
"sentinel-scan-cli"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"sentinel-scan": {
"command": "npx",
"args": [
"-y",
"sentinel-scan-cli"
]
}
}
}