Security Detections runs on your own machine — the client starts it, so there is no endpoint to ping. 1 213 installs a week from npm. Last commit 4 Nov 2026.
Search security detections across Sigma, Splunk, Elastic, KQL, Sublime, CQL and Jamf with ATT&CK.
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
'CurrentVersion\\Run',
'https://cursor.com/en/install-mcp?name=security-detections-hosted&config=eyJ1cmwiOiJodHRwczovL2RldGVjdC5taWNoYWVsaGFhZy5vcmcvYXBpL21jcC9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgc2RtY3BfWU9VUl9UT0tFTl9IRVJFIn19';
db.exec(`INSERT INTO detections_identity_new(rowid, ${info.map(c => '"' + c.name.replaceAll('"', '""') + '"').join(', ')}) SELECT rowid, * FROM detections`);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add security-detections-mcp -- npx -y security-detections-mcp
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}
[mcp_servers.security-detections-mcp]
command = "npx"
args = ["-y", "security-detections-mcp"]
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}
{
"servers": {
"security-detections-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SIGMA_PATHS (Comma-separated paths to Sigma rule directories (e.g., /path/to/sigma/rules,/path/to/sigma/rules-threat-hunting)), SPLUNK_PATHS (Comma-separated paths to Splunk ESCU detection directories (e.g., /path/to/security_content/detections)), ELASTIC_PATHS (Comma-separated paths to Elastic detection rule directories (e.g., /path/to/detection-rules/rules)), KQL_PATHS (Comma-separated paths to KQL hunting query directories (e.g., /path/to/kql-queries)), SUBLIME_PATHS (Comma-separated paths to Sublime MQL rule directories (e.g., /path/to/sublime-rules/detection-rules,/path/to/delivr-detections/sublime-rules)), CQL_HUB_PATHS (Comma-separated paths to CQL Hub (CrowdStrike) query directories (e.g., /path/to/cql-hub/queries)), JAMF_PROTECT_PATHS (Comma-separated paths to Jamf Protect custom analytic detection directories (macOS, e.g., /path/to/jamfprotect/custom_analytic_detections)), STORY_PATHS (Comma-separated paths to Splunk analytic story directories (optional, e.g., /path/to/security_content/stories)).
Deterministic authorization and security guard for AI agent actions with signed receipts.
AWS security scanner with attack chain detection, IAM privilege escalation, and fixes
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Security-hardened file organizer with smart categorization and duplicate detection
1,451 security controls across 261 frameworks with bidirectional mapping
Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS
Professional network analysis with tshark. Security audits, deep-dives, and threat detection.
Security scanning and threat detection for AI agents
Answers built from our own checks of this server.