Security Detections
Search 8,200+ detection rules across Sigma, Splunk, Elastic, KQL and more, via ATT&CK
- Pricing
- Freemium
- Platforms
- CLI, API
- Runs
- Locally
- Version
- 3.3.4
- Listing updated
- today
Similar MCP servers
About Security Detections
Security Detections is a freemium MCP server for security. It runs locally on your machine and is started by your AI client.
Detection engineers usually keep rules in several incompatible repositories. This server indexes your own checkouts of those repos into one local database, so an assistant can search them together and tie results to MITRE ATT&CK. Point SIGMA_PATHS, SPLUNK_PATHS, ELASTIC_PATHS, KQL_PATHS, SUBLIME_PATHS, CQL_HUB_PATHS, JAMF_PROTECT_PATHS and optional STORY_PATHS at the folders.
The local package exposes 81 tools, with ATT&CK data on 172 threat actors and 784 software entries, procedure-level coverage clusters, Navigator layer export and 11 MCP prompts for jobs like ransomware assessment and purple-team planning. A hosted option trims this to around 25 read-only tools for 200 calls a day on a free tier, with a token from the maintainer's site.
The repo also describes an autonomous pipeline that goes from threat intel to gap analysis, rule drafting and a draft pull request, plus a web chat with free and bring-your-own-key model routing.
Install
Run in a terminal
claude mcp add security-detections-mcp -- npx -y security-detections-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"security-detections-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"security-detections-mcp": {
"command": "npx",
"args": [
"-y",
"security-detections-mcp"
]
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
SIGMA_PATHSComma-separated paths to Sigma rule directories (e.g., /path/to/sigma/rules,/path/to/sigma/rules-threat-hunting)SPLUNK_PATHSComma-separated paths to Splunk ESCU detection directories (e.g., /path/to/security_content/detections)ELASTIC_PATHSComma-separated paths to Elastic detection rule directories (e.g., /path/to/detection-rules/rules)KQL_PATHSComma-separated paths to KQL hunting query directories (e.g., /path/to/kql-queries)SUBLIME_PATHSComma-separated paths to Sublime MQL rule directories (e.g., /path/to/sublime-rules/detection-rules,/path/to/delivr-detections/sublime-rules)CQL_HUB_PATHSComma-separated paths to CQL Hub (CrowdStrike) query directories (e.g., /path/to/cql-hub/queries)JAMF_PROTECT_PATHSComma-separated paths to Jamf Protect custom analytic detection directories (macOS, e.g., /path/to/jamfprotect/custom_analytic_detections)STORY_PATHSComma-separated paths to Splunk analytic story directories (optional, e.g., /path/to/security_content/stories)
What it does
- Unified rule search
- Query Sigma, Splunk ESCU, Elastic, KQL, Sublime, CQL and Jamf Protect rules in one place.
- ATT&CK mapping
- Includes STIX data on threat actors, software and actor-technique links.
- Coverage and gaps
- Export ATT&CK Navigator layers filtered by source, tactic, severity or actor.
- Local or hosted
- Run all 81 tools locally, or use a hosted server with about 25 read-only tools.
- Prompts and resources
- 11 prompts plus readable resources and technique-ID autocomplete.
- Autonomous pipeline
- Optional flow from CTI to a draft pull request, documented in the repo.
Good for
- Find existing detections for a given ATT&CK technique before writing a new one
- Spot coverage gaps against a specific threat actor
- Compare how Sigma and Splunk express the same behaviour
- Prepare an executive or purple-team briefing from rule data
Pricing
Freemium
Hosted free tier: 200 calls a day; local npm package runs on your machine
Security Detections FAQ
What does the hosted version cost?
Its README lists a free tier of 200 calls a day with all read-only tools; other pricing is not published.
Do I need to supply the rules?
For the local server yes, via the path variables; the hosted one is kept current for you.
How many tools are there?
81 locally and roughly 25 hosted.
Which clients are covered?
Install snippets are given for Cursor, VS Code, Claude Code, Claude Desktop and OpenAI Codex.
Is Security Detections free?
Security Detections has a free plan, with paid plans for more usage or features.
How do I add Security Detections to Claude Code?
Run this command in your terminal: claude mcp add security-detections-mcp -- npx -y security-detections-mcp
What are the best alternatives to Security Detections?
The closest alternatives to Security Detections are REA, AiSOC, redamon, x64dbg-mcp-server and Agent Roast.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.



