KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#typescript #ai-agents #cli #open-source #ai #claude-code #codex #developer-tools #react #windows #deepseek-harness #ai-agent

CrowdSentinels-AI-MCP

★ 206 Open GitHub ↗

AI-powered threat hunting and incident response MCP server for Elasticsearch/OpenSearch

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# CrowdSentinel MCP Server

### AI-Powered Threat Hunting & Incident Response Framework

[![PyPI](https://img.shields.io/pypi/v/crowdsentinel-mcp-server.svg)](https://pypi.org/project/crowdsentinel-mcp-server/)
[![PyPI Downloads](https://img.shields.io/pypi/dm/crowdsentinel-mcp-server.svg)](https://pypi.org/project/crowdsentinel-mcp-server/)
[![Python](https://img.shields.io/pypi/pyversions/crowdsentinel-mcp-server?cacheSeconds=3600)](https://pypi.org/project/crowdsentinel-mcp-server/)
[![License](https://img.shields.io/badge/License-GPL%20v3-blue.svg)](https://raw.githubusercontent.com/thomasxm/CrowdSentinels-AI-MCP/main/LICENSE)
[![MCP](https://img.shields.io/badge/MCP-Compatible-purple.svg)](https://modelcontextprotocol.io/)
[![Tools](https://img.shields.io/badge/MCP%20Tools-139-brightgreen.svg)](https://github.com/thomasxm/CrowdSentinels-AI-MCP)
[![Rules](https://img.shields.io/badge/Detection%20Rules-6%2C060-blue.svg)](https://github.com/thomasxm/CrowdSentinels-AI-MCP)

[![Install from PyPI](https://img.shields.io/badge/Install-pip%20install%20crowdsentinel--mcp--server-3775A9?style=for-the-badge&logo=pypi&logoColor=white)](https://pypi.org/project/crowdsentinel-mcp-server/)

[MCP Official Registry](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.thomasxm/crowdsentinel-mcp-server) · [PyPI Package](https://pypi.org/project/crowdsentinel-mcp-server/)

**Open-source threat hunting orchestrator connecting LLMs to enterprise security data via Model Context Protocol (MCP)**

[Quick Start](#quick-start) · [Installation](#installation) · [CLI Usage](#cli-usage) · [Features](#key-features) · [Architecture](#architecture) · [Documentation](#documentation) · [Examples](#usage-examples)

</div>

> **Warning**
> This project is in active development and intended for **security testing, research, and educational purposes only**. It is not production-ready. Do not deploy in production environments. APIs, tool interfaces, and data formats may change without notice. Use at your own risk.

---

## Demo

https://github.com/user-attachments/assets/0d0381f0-5b68-43b2-8630-19ec130885b2

---

## What is CrowdSentinel?

**CrowdSentinel** transforms traditional SIEM querying into intelligent, framework-driven investigations using natural language. It serves as a unified security intelligence layer that connects large language models to enterprise security data sources, enabling:

- **Natural Language Threat Hunting** — Query Elasticsearch using plain English
- **AI-Guided Investigation Workflows** — Built-in prompts guide agents through proper IR methodology
- **Persistent Investigation State** — Memory-managed IoC tracking, forensic timelines, and cross-query correlation that survives across sessions (8GB FIFO storage)
- **Cross-Tool IoC Correlation** — IoCs discovered in one tool are automatically available to all others
- **Multi-Source Analysis** — Elasticsearch, EVTX logs (Chainsaw), PCAP files (Wireshark), live endpoint forensics (Velociraptor), local host forensics (osquery)
- **Velociraptor Endpoint Forensics** — 25 MCP tools for live artefact collection (processes, network, persistence, execution evidence, NTFS MFT, SRUM, remote EVTX) with automatic IoC extraction
- **Encoded-Command Deobfuscation** — Automatically peels base64/UTF-16LE/gzip/hex layers off encoded commands (e.g. PowerShell `-EncodedCommand`) so C2 addresses hidden inside them surface as IoCs
- **Adaptive Schema Intelligence** — Data-driven schema registry (ECS, Sysmon, Windows Security, auditd, Zeek, Packetbeat, AWS CloudTrail) adapts hunts to each index's field conventions
- **DFIR Knowledge Resources** — 9 MCP resources exposing investigation playbooks, Pyramid of Pain reference, and cross-correlation guidance directly to connected AI agents
- **Standalone CLI** — Full threat hunting from the terminal without an MCP client

---

<a name="installation"></a>
## Installation

### Install from PyPI (recommended)

```bash
# Install with pip
pip install crowdsentinel-mcp-server

# Or install with uv
uv pip install crowdsentinel-mcp-server

# Download detection rules, Chainsaw, and Sigma rules (one-time)
crowdsentinel setup

# Validate connector configuration and readiness (offline, no external calls)
crowdsentinel doctor
```

**Optional extras:**

```bash
# Velociraptor live endpoint forensics (adds 25 MCP tools)
pip install 'crowdsentinel-mcp-server[velociraptor]'

# Long-tail deobfuscation coverage via chepy (XOR, exotic encodings).
# The stdlib decoder core works without this — chepy only extends it.
pip install 'crowdsentinel-mcp-server[deobf]'
```

Detection rules (6,060 Lucene + EQL + ES|QL) are **bundled with the package** — no download needed. The `setup` command downloads additional tools:
- Chainsaw binary for EVTX analysis
- 3,000+ Sigma rules for Chainsaw

Downloaded tools are stored in `~/.crowdsentinel/` and persist across package upgrades.

**System dependency for PCAP analysis:**

```bash
# Required for network traffic analysis and cross-tool IoC correlation
sudo apt install tshark    # Debian/Ubuntu/Kali
sudo dnf install wireshark-cli  # Fedora/RHEL
brew install wireshark     # macOS
```

### Run directly with uvx (no install needed)

```bash
# Elasticsearch 8.x (default)
uvx crowdsentinel-mcp-server

# Other backends
uvx crowdsentinel-mcp-server-es7   # Elasticsearch 7.x
uvx crowdsentinel-mcp-server-es9   # Elasticsearch 9.x
uvx opensearch-mcp-server          # OpenSearch 1.x/2.x/3.x
```

### Install from source

```bash
git clone https://github.com/thomasxm/CrowdSentinels-AI-MCP.git
cd CrowdSentinels-AI-MCP
chmod +x setup.sh && ./setup.sh

# Or install everything, including all optional extras (deobf/chepy, velociraptor)
./setup.sh --full
```

The setup script will:
- Install dependencies (pipx, uv, Claude Code CLI if needed)
- Bundle 6,060 detection rules and download Chainsaw binary
- Prompt for Elasticsearch credentials (never hardcoded)
- Configure the MCP server with Claude Code
- Validate your connection

With `--full`, every optional extra is installed too, so all 139 MCP tools have their dependencies available — the recommended mode for a production-ready server.

### Installed Size

CrowdSentinel bundles 6,060 detection rules and integrates with external analysis tools. Below is the full disk space breakdown so you can plan accordingly.

**Core package (via `pip` or `uvx`):**

| Component | Size | Notes |
|---|---|---|
| **CrowdSentinel package** | **49 MB** | The server itself |
| — Bundled Sigma rules (`src/rules/`) | 30 MB | 6,060 pre-converted detection rules |
| — Elastic TOML rules (`src/detection-rules/`) | 17 MB | Original TOML format rules + hunting queries |
| — Python code (clients, tools, etc.) | 2 MB | Actual application code |
| **Dependencies** | **64 MB** | All transitive deps |
| — `cryptography` | 14 MB | Largest dependency (TLS) |
| — `elasticsearch` | 8.3 MB | ES Python client |
| — `pygments` | 5.2 MB | Syntax highlighting |
| — `pydantic_core` | 5 MB | Validation engine |
| — `opensearchpy` | 3.6 MB | OpenSearch client |
| — Others (27 packages) | ~28 MB | mcp, fastmcp, httpx, anthropic, etc. |
| **Core total** | **113 MB** | `pip install crowdsentinel-mcp-server` |

**Additional tools (via `crowdsentinel setup`):**

| Component | Download | Installed | Notes |
|---|---|---|---|
| Chainsaw binary (v2.13.1) | ~3 MB | ~15 MB | EVTX log analysis engine |
| Sigma rules (SigmaHQ) | ~3 MB | ~30 MB | 3,000+ Sigma rules for Chainsaw |
| Chainsaw mappings | — | <1 MB | Event log source mappings |
| **Setup total** | **~6 MB** | **~46 MB** | Stored in `~/.crowdsentinel/` |

**System dependency (via package manager):**

| Component | Installed | Install Command | Notes |
|---|---|---|---|
| tshark + Wireshark libs | ~132 MB | `sudo apt install tshark` | PCAP network analysis — required for cross-tool IoC correlation |

**Full installation summary:**

| Scenario | Total Disk Space |
|---|---|
| Core only (`pip install`) | ~113 MB |
| Core + setup (`crowdsentinel setup`) | ~159 MB |
| Full platform (+ tshark) | **~291 MB** |

> **Note:** PyPI download size is only **8.9 MB** (wheel) thanks to compression of the bundled detection rules.

---

<a name="quick-start"></a>
## Quick Start

### 1. Set environment variables

```bash
export ELASTICSEARCH_HOSTS="https://localhost:9200"
export ELASTICSEARCH_API_KEY="your_api_key"
# Or use username/password:
# export ELASTICSEARCH_USERNAME="elastic"
# export ELASTICSEARCH_PASSWORD="your_password"
export VERIFY_CERTS="false"
```

### 2. Connect to an MCP Client

CrowdSentinel works with any MCP-compatible AI agent. Choose your client below:

<details>
<summary>Claude Code (CLI)</summary>

```bash
claude mcp add crowdsentinel \
 -e ELASTICSEARCH_HOSTS="https://localhost:9200" \
 -e ELASTICSEARCH_API_KEY="your_api_key" \
 -e VERIFY_CERTS="false" \
 -- uvx crowdsentinel-mcp-server
```
</details>

<details>
<summary>Claude Desktop</summary>

Edit `~/.config/Claude/claude_desktop_config.json` (Linux) or `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):

```json
{
 "mcpServers": {
 "crowdsentinel": {
 "command": "uvx",
 "args": ["crowdsentinel-mcp-server"],
 "env": {
 "ELASTICSEARCH_HOSTS": "https://localhost:9200",
 "ELASTICSEARCH_API_KEY": "your_api_key",
 "VERIFY_CERTS": "false"
 }
 }
 }
}
```
</details>

<details>
<summary>VS Code Copilot</summary>

Create `.vscode/mcp.json` in your workspace:

```json
{
  "servers": {
    "crowdsentinel": {
      "command": "uvx",
      "args": ["crowdsentinel-mcp-server"],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_API_KEY": "your_api_key",
        "VERIFY_CERTS": "false"
      }
    }
  }
}
```

Then enable MCP in VS Code settings: `"chat.mcp.enabled": true`
</details>

<details>
<summary>Cursor</summary>

Create or edit `~/.cursor/mcp.json`:

<details>
<summary>Roo Code (VS Code Extension)</summary>

Create `.roo/mcp.json` in your workspace:

Or configure via Roo Code settings panel: Settings > MCP Servers > Add Server.
</details>

In 5ire settings (v0.15.0+), add an MCP server with:

- **Command**: `uvx`
- **Arguments**: `crowdsentinel-mcp-server`
- **Environment Variables**:
  - `ELASTICSEARCH_HOSTS` = `https://localhost:9200`
  - `ELASTICSEARCH_API_KEY` = `your_api_key`
  - `VERIFY_CERTS` = `false`

> **Note:** 5ire v0.14.0 has known MCP compatibility issues. Use v0.15.0+ for reliable operation.
</details>

<details>
<summary>Any MCP Client (Generic)</summary>

**stdio transport** (default — works with most clients):
```json
{
  "mcpServers": {
    "crowdsentinel": {
      "command": "uvx",
      "args": ["crowdsentinel-mcp-server"],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_API_KEY": "your_api_key",
        "VERIFY_CERTS": "false"
      }
    }
  }
}
```

**SSE transport** (for web-based clients):
```bash
crowdsentinel-mcp-server --transport sse --port 8001
# Connect to: http://localhost:8001/sse/
```

**HTTP transport** (for REST API clients):
```bash
crowdsentinel-mcp-server --transport streamable-http --port 8001
# Connect to: http://localhost:8001/mcp/
```
</details>

### 3. Or use the CLI directly

```bash
# Download rules and tools (one-time)
crowdsentinel setup

# Check cluster health
crowdsentinel health

# Hunt for threats
crowdsentinel hunt "powershell encoded" -i winlogbeat-*

# Run detection rules
crowdsentinel rules -p windows --tactic credential_access
crowdsentinel detect windows_builtin_win_alert_mimikatz_keywords_lucene -i winlogbeat-*

# Analyse PCAP files
crowdsentinel pcap overview capture.pcap
crowdsentinel pcap beaconing capture.pcap

# Hunt EVTX logs with Chainsaw
crowdsentinel chainsaw hunt /path/to/evtx/ --sigma-rules /path/to/sigma/
```

---

<a name="cli-usage"></a>
## CLI Usage

CrowdSentinel provides a full CLI for threat hunting from the terminal:

```bash
pip install crowdsentinel-mcp-server
crowdsentinel setup    # Download rules, Chainsaw, Sigma (one-time)
crowdsentinel --help
```

### Available Commands

| Command | Description | Example |
|:--------|:------------|:--------|
| `setup` | Download detection rules, Chainsaw, and Sigma rules | `crowdsentinel setup` |
| `health` | Show cluster health | `crowdsentinel health` |
| `indices` | List all indices | `crowdsentinel indices` |
| `hunt` | IR-focused threat hunt with IoC extraction | `crowdsentinel hunt "powershell" -i winlogbeat-*` |
| `eql` | Execute an EQL query | `crowdsentinel eql "process where process.name == 'cmd.exe'" -i winlogbeat-*` |
| `esql` | Execute an ES\|QL query | `crowdsentinel esql "FROM logs-* \| LIMIT 10"` |
| `detect` | Execute a detection rule by ID | `crowdsentinel detect win_susp_logon -i winlogbeat-*` |
| `rules` | List available detection rules | `crowdsentinel rules -p windows --tactic credential_access --type eql` |
| `schema` | Detect schema for an index pattern | `crowdsentinel schema -i winlogbeat-*` |
| `ioc` | Hunt for a specific Indicator of Compromise | `crowdsentinel ioc 203.0.113.42 --type ip -i winlogbeat-*` |
| `analyse` | Analyse search results from stdin (JSON) | `cat results.json \| crowdsentinel analyse -c "context"` |
| `analyse --mcp` | AI agent analysis using all 139 MCP tools | `crowdsentinel hunt "query" \| crowdsentinel analyse --mcp -c "context"` |
| `auth` | Manage LLM authentication for agent mode | `crowdsentinel auth login` |
| `pcap` | Analyse PCAP files (overview, beaconing, lateral movement) | `crowdsentinel pcap beaconing capture.pcap` |
| `chainsaw` | Hunt EVTX logs with Chainsaw and Sigma rules | `crowdsentinel chainsaw hunt /path/to/evtx/` |
| `doctor` | Validate connector configuration and readiness (offline — no external calls) | `crowdsentinel doctor` |

### Output Formats

All commands support `--output/-o` with three formats:

```bash
crowdsentinel hunt "failed login" -i winlogbeat-* -o json     # Structured JSON (default)
crowdsentinel hunt "failed login" -i winlogbeat-* -o table    # Human-readable table
crowdsentinel hunt "failed login" -i winlogbeat-* -o summary  # Condensed summary
```

### Agent Mode (`--mcp`)

The `analyse --mcp` flag replaces deterministic analysis with an AI agent that autonomously uses all 139 MCP tools to investigate. The agent follows the 4-phase IR methodology: hunt, analyse, correlate, report.

**Authentication:**

```bash
# Option 1: Browser sign-in (ChatGPT subscription — no API billing)
crowdsentinel auth login

# Option 2: Anthropic (setup-token or API key)
crowdsentinel auth login --provider anthropic

# Option 3: Environment variable
export ANTHROPIC_API_KEY="sk-ant-..."   # or OPENAI_API_KEY

# Option 4: Local models (Ollama, vLLM — free)
crowdsentinel analyse --mcp --model-url http://localhost:11434/v1 --model llama3.1

# Check auth status
crowdsentinel auth status
```

**Agent flags:**

| Flag | Default | Description |
|:-----|:--------|:------------|
| `--mcp` | off | Enable AI agent with MCP tools |
| `--mcp-server NAME:CMD` | none | Add external MCP server (e.g., VirusTotal) |
| `--model` | auto-detect | LLM model to use |
| `--model-url` | none | OpenAI-compatible API endpoint |
| `--max-steps` | 30 | Maximum tool calls |
| `--timeout` | 300 | Maximum seconds |

### Pipeline Examples

**Deterministic analysis (no API key needed):**

```bash
# Hunt then analyse
crowdsentinel hunt "powershell encoded" -i winlogbeat-* -o json | \
  crowdsentinel analyse -c "Encoded PowerShell commands" -o summary

# Investigate failed authentication attempts
crowdsentinel hunt "event.code:4625" -i winlogbeat-* -o json | \
  crowdsentinel analyse -c "Failed login brute force investigation" -o summary

# Triage process execution and privilege escalation
crowdsentinel hunt "event.code:4688 OR event.code:4672 OR event.code:1" -i winlogbeat-* -o json | \
  crowdsentinel analyse -c "Process execution and privilege escalation" -o summary
```

**AI agent investigation (requires auth):**

```bash
# Credential dumping investigation — agent hunts, analyses kill chain, checks adjacent stages
crowdsentinel hunt "mimikatz OR lsass OR procdump" -i winlogbeat-* -o json | \
  crowdsentinel analyse --mcp -c "Credential dumping tools investigation" --max-steps 15 -o summary

# Encoded PowerShell — full IR workflow with kill chain and adjacent stage hunting
crowdsentinel hunt "powershell -enc OR FromBase64String" -i winlogbeat-* -o json | \
  crowdsentinel analyse --mcp -c "Full IR workflow: encoded PowerShell" --max-steps 30 -o table

# Process execution with detection rules
crowdsentinel hunt "event.code:4688" -i winlogbeat-* -o json | \
  crowdsentinel analyse --mcp -c "Execute detection rules against process creation" --max-steps 20 -o summary

# PCAP beaconing — agent generates IoCs and maps to kill chain
crowdsentinel pcap beaconing capture.pcap -o json | \
  crowdsentinel analyse --mcp -c "Investigate beaconing for C2 infrastructure" --max-steps 10 -o summary

# Anti-forensics investigation
crowdsentinel hunt "event.code:1102" -i winlogbeat-* -o json | \
  crowdsentinel analyse --mcp -c "Security log cleared - anti-forensics" --max-steps 10 -o summary

# With external MCP server (e.g., VirusTotal)
crowdsentinel hunt "powershell" -i winlogbeat-* -o json | \
  crowdsentinel analyse --mcp --mcp-server "vt:uvx virustotal-mcp-server" \
  -c "Check IoCs against VirusTotal" -o summary
```

---

<a name="key-features"></a>
## Key Features

### 139 MCP Tools
Threat hunting, detection rules, forensics, endpoint collection, network analysis, cross-correlation, command deobfuscation, and IoC enrichment — all accessible via natural language

### 6,060 Detection Rules
Pre-built Lucene, EQL & ES|QL rules with automatic MITRE ATT&CK mapping

### Investigation State
Persistent IoC tracking across tools and sessions with cross-source correlation and FIFO storage

</td>
<td width="50%">

### 4 Security Frameworks
- Cyber Kill Chain (7 stages)
- Pyramid of Pain (6 levels)
- Diamond Model (4 vertices)
- MITRE ATT&CK (automatic mapping)

### 5 Data Sources + Threat Intel
- Elasticsearch / OpenSearch (SIEM)
- Velociraptor (live endpoint forensics)
- osquery (local host forensics)
- EVTX logs (Chainsaw + Sigma)
- PCAP files (Wireshark/TShark)
- IoC enrichment (Shodan, VirusTotal, AbuseIPDB, ThreatFox)
- MISP (export events, search attributes)

</td>
</tr>
</table>

---

<a name="architecture"></a>
## Architecture

```
┌─────────────────────────────────────────────────────────────────┐
│                 LLM Client / Claude Code CLI                    │
└─────────────────────────────┬───────────────────────────────────┘
                              │ MCP Protocol (stdio/SSE/HTTP)
                              │ HTTP: Origin validation (anti DNS-rebinding)
                              │       + transport-level audit logging
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                    CrowdSentinel MCP Server                     │
│  ┌───────────────┐ ┌───────────────┐ ┌───────────────────────┐  │
│  │  139 Tools    │ │ 6,060 Rules   │ │ Security Frameworks   │  │
│  │ - Hunting     │ │ - Lucene      │ │ - Cyber Kill Chain    │  │
│  │ - Detection   │ │ - EQL         │ │ - Pyramid of Pain     │  │
│  │ - Forensics   │ │ - ES|QL       │ │ - Diamond Model       │  │
│  │ - Endpoint    │ │               │ │ - MITRE ATT&CK        │  │
│  │ - Network     │ ├───────────────┤ │                       │  │
│  │ - Enrichment  │ │ Schema        │ │ 9 MCP Resources       │  │
│  │ - Correlation │ │ Registry      │ │ (DFIR knowledge base) │  │
│  │ - Deobfuscate │ │ (data-driven) │ │                       │  │
│  └───────────────┘ └───────────────┘ └───────────────────────┘  │
│  ┌─────────────────────────────────────────────────────────────┐│
│  │              Investigation State (Persistent)               ││
│  │    Cross-source IoC sharing, auto-capture, STIX 2.1 export  ││
│  └─────────────────────────────────────────────────────────────┘│
└─────┬──────────┬──────────┬──────────────┬─────────────┬────────┘
      │          │          │              │             │
      ▼          ▼          ▼              ▼             ▼
┌───────────┐ ┌──────────┐ ┌────────┐ ┌───────────┐ ┌───────────┐
│Elastic-   │ │Velocirap-│ │osquery │ │ Chainsaw  │ │ Wireshark │
│search/    │ │tor       │ │(local  │ │(EVTX/     │ │  (PCAP)   │
│OpenSearch │ │(EDR/DFIR)│ │ host)  │ │ Sigma)    │ │ (Network) │
│  (SIEM)   │ │(Endpoint)│ │        │ │(Offline)  │ │           │
└───────────┘ └──────────┘ └────────┘ └───────────┘ └───────────┘
                          │
  ┌───────────────────────┼───────────────────────┐
  ▼                       ▼                       ▼
┌───────────────┐ ┌───────────────┐ ┌───────────────────────────┐
│ Shodan        │ │  VirusTotal   │ │  AbuseIPDB + ThreatFox    │
│ InternetDB    │ │     (v3)      │ │  + MISP (export/search)   │
│  (free/no key)│ │  (free tier)  │ │  (free tier)              │
└───────────────┘ └───────────────┘ └───────────────────────────┘
                          │
                          ▼ (Roadmap)
┌───────────────┐ ┌───────────────┐ ┌───────────────┐
│    Splunk     │ │     Wazuh     │ │     Zeek      │
│               │ │  (EDR/XDR)    │ │   (NSM/IDS)   │
└───────────────┘ └───────────────┘ └───────────────┘
```

---

## What's Included

### Tool Categories (139 Tools)

| Category | Tools | Description |
|:---------|:-----:|:------------|
| **Elasticsearch Core** | 19 | Index, document, cluster, alias, data stream, raw API operations |
| **Threat Hunting** | 8 | Attack pattern detection, kill-chain stage hunting, timeframe hunts, anomaly detection |
| **EQL & ES\|QL Hunting** | 11 | Event-sequence queries, ES\|QL pipes, saved hunt history, capability detection |
| **Asset Discovery & Schema Intelligence** | 12 | Index discovery, data-driven schema detection (ECS, Sysmon, auditd, Zeek, CloudTrail…), smart search |
| **IoC Analysis & Deobfuscation** | 6 | IoC extraction, encoded-command decoding, kill-chain mapping, investigation reports |
| **Detection Rules** | 9 | 6,060 rule library — list, execute, validate, suggest, batch execution |
| **Investigation Prompts** | 5 | Fast triage spine — 10 critical IR questions |
| **Chainsaw (EVTX)** | 5 | Sigma rule hunting, iterative IoC discovery |
| **Wireshark (PCAP)** | 11 | Network forensics, beaconing, lateral movement detection, traffic decoding |
| **Threat Intelligence** | 5 | IoC enrichment (Shodan, VirusTotal, AbuseIPDB, ThreatFox) + MISP export/search |
| **Investigation State** | 10 | Persistent IoCs, cross-tool sharing, STIX 2.1 export, reporting |
| **Velociraptor (Endpoint)** | 25 | Live forensic artefact collection — processes, network, persistence, execution evidence, MFT, SRUM |
| **osquery (Local Host)** | 4 | SQL-based local host forensics — processes, sockets, users, ad-hoc queries |
| **Cross-Source Correlation** | 5 | SIEM ↔ endpoint pivots, IoC-driven endpoint hunts, unified timelines, time correlation |
| **Workflow Guidance & Status** | 4 | Next-step guidance, progressive disclosure, system status, storage cleanup |

> Velociraptor tools register when `VELOCIRAPTOR_API_CONFIG` is set; osquery tools register when a local `osqueryi` binary is present; the 10 high-risk write tools are hidden when `DISABLE_HIGH_RISK_OPERATIONS=true`.

### Security Frameworks

| Framework | Purpose |
|:----------|:--------|
| **Cyber Kill Chain** | Hunt by attack stage (7 stages), predict adversary's next move |
| **Pyramid of Pain** | Prioritise IoCs by difficulty for attackers to change (6 levels) |
| **Diamond Model** | Map adversary, capability, infrastructure, victim relationships |
| **MITRE ATT&CK** | Automatic technique mapping for all detections |

### Detection Rules (6,060 Rules)

| Type | Count | Source | Description |
|:-----|------:|:-------|:------------|
| **Lucene** | 1,966 | Sigma-converted | Fast pattern matching queries |
| **EQL** | 3,963 | Sigma-converted + Elastic | Event sequences and correlations |
| **ES\|QL** | 131 | Elastic TOML rules | Pipe-based query language (ES 8.11+) |

**Platforms:** Windows, Linux, macOS, Cloud (AWS/Azure/GCP), Network, Identity

**Log Sources:** PowerShell, Sysmon, Security Events, Process Creation, Audit logs

### Encoded-Command Deobfuscation

Real intrusions hide C2 addresses and URLs inside encodings the SIEM stores verbatim — most commonly PowerShell `-EncodedCommand` (base64 of UTF-16LE), but also `FromBase64String`, base64→gzip, bare base64, and hex blobs. CrowdSentinel decodes these layers automatically during IoC extraction and via the dedicated `decode_command` tool, so the inner indicators surface instead of staying buried:

- **Zero extra dependencies** — the decoder core uses only the Python standard library (`base64`/`zlib`/`codecs`/`binascii`)
- **Optional long tail** — install the `deobf` extra (`pip install 'crowdsentinel-mcp-server[deobf]'`) to add [chepy](https://github.com/securisec/chepy) for XOR and exotic encodings; its absence degrades gracefully
- **Provenance** — every decode records its recipe (e.g. `base64->utf-16le`) for the IR report
- **Safe by design** — decode-only (nothing is executed), with depth and output-size bounds so a decompression bomb cannot hang the server

---

## Configuration

### Environment Variables

```bash
# Connection (required — choose one)
ELASTICSEARCH_HOSTS="https://localhost:9200"       # Self-hosted
# OR
ELASTICSEARCH_CLOUD_ID="deployment:base64..."      # Elastic Cloud

# Authentication — choose one (in priority order):
ELASTICSEARCH_BEARER_TOKEN="service_token_here"    # Service/bearer token
ELASTICSEARCH_API_KEY="your_api_key"               # API key (recommended)
ELASTICSEARCH_USERNAME="elastic"                   # Basic auth
ELASTICSEARCH_PASSWORD="your_password"

# TLS / Certificate verification
VERIFY_CERTS="true"                                # Verify against system CA bundle
# VERIFY_CERTS="/path/to/ca.crt"                   # Verify against custom CA certificate
# ELASTICSEARCH_CA_CERT="/path/to/ca.crt"          # Explicit CA certificate path
# ELASTICSEARCH_CLIENT_CERT="/path/to/client.crt"  # Client certificate (mTLS)
# ELASTICSEARCH_CLIENT_KEY="/path/to/client.key"   # Client private key (mTLS)

# Options
REQUEST_TIMEOUT="30"                               # Request timeout in seconds
DISABLE_HIGH_RISK_OPERATIONS="true"                # Block all write operations

# HTTP/SSE transport security (stdio unaffected)
# MCP_ALLOWED_ORIGINS="https://app.example.com"    # Extra allowed Origins (comma-separated); loopback always allowed

# Velociraptor endpoint forensics (optional — enables 25 extra tools)
# VELOCIRAPTOR_API_CONFIG="/path/to/api_client.yaml"

# Threat Intelligence (optional — Shodan InternetDB works without any key)
VIRUSTOTAL_API_KEY="your_vt_key"                   # Free: 500 lookups/day
ABUSEIPDB_API_KEY="your_abuse_key"                 # Free: 1,000 lookups/day
THREATFOX_API_KEY="your_tf_key"                    # Free: unlimited

# MISP Integration (optional — offline JSON export works without a server)
MISP_URL="https://misp.example.org"                # MISP instance URL
MISP_API_KEY="your_misp_key"                       # MISP API key (40-char hex)
# MISP_SSL_VERIFY="true"                           # Set "false" for self-signed (dev only)
```

> **Security Warning:** Never use `VERIFY_CERTS="false"` or plain-text passwords in production. Use API keys or service tokens with TLS certificate verification enabled. For self-signed certificates, set `ELASTICSEARCH_CA_CERT` to your CA certificate path.

### Production Configuration Examples

<details>
<summary>Elastic Cloud</summary>

```bash
ELASTICSEARCH_CLOUD_ID="my-deployment:dXMtY2VudHJhbC0x..."
ELASTICSEARCH_API_KEY="your_cloud_api_key"
VERIFY_CERTS="true"
```
</details>

<details>
<summary>Self-Hosted with Custom CA</summary>

```bash
ELASTICSEARCH_HOSTS="https://es-cluster.internal:9200"
ELASTICSEARCH_API_KEY="your_api_key"
ELASTICSEARCH_CA_CERT="/etc/elasticsearch/certs/ca.crt"
VERIFY_CERTS="true"
```
</details>

<details>
<summary>Mutual TLS (mTLS)</summary>

```bash
ELASTICSEARCH_HOSTS="https://es-cluster.internal:9200"
ELASTICSEARCH_CA_CERT="/etc/elasticsearch/certs/ca.crt"
ELASTICSEARCH_CLIENT_CERT="/etc/elasticsearch/certs/client.crt"
ELASTICSEARCH_CLIENT_KEY="/etc/elasticsearch/certs/client.key"
VERIFY_CERTS="true"
```
</details>

<details>
<summary>Development / Testing (insecure)</summary>

```bash
ELASTICSEARCH_HOSTS="http://localhost:9200"
ELASTICSEARCH_USERNAME="elastic"
ELASTICSEARCH_PASSWORD="test123"
VERIFY_CERTS="false"
```

> This configuration is **not suitable for production**. Use API keys with TLS in production environments.
</details>

### Transport Modes

| Mode | Use Case | Command |
|:-----|:---------|:--------|
| **stdio** (default) | MCP clients (Claude Code, etc.) | Auto-configured by setup.sh |
| **SSE** | Web/streaming clients | `--transport sse --port 8000` |
| **HTTP** | REST API access | `--transport streamable-http` |

The HTTP transports are hardened at the transport layer:

- **Origin validation (anti DNS-rebinding)** — browser requests are rejected unless their `Origin` is loopback or listed in `MCP_ALLOWED_ORIGINS` (comma-separated; `*` alone disables the check). Requests without an `Origin` header — every non-browser MCP client — are unaffected.
- **Audit logging** — every HTTP exchange is logged at the transport boundary (JSON-RPC method, tool name, body size, path), including requests the tool layer never sees, such as unknown tools or protocol errors. Logs are metadata-only, memory-bounded, and sanitised against log forgery.

### Disabling Write Operations

For read-only access (recommended for production):

```bash
DISABLE_HIGH_RISK_OPERATIONS="true"
```

This hides destructive tools: `create_index`, `delete_index`, `index_document`, `delete_document`, `delete_by_query`, `create_data_stream`, `delete_data_stream`, `put_alias`, `delete_alias`, `general_api_request`

---

<a name="usage-examples"></a>
## Usage Examples

### Example 1: Hunt for Brute Force Attacks

```
You: Hunt for brute force attacks in the last hour

CrowdSentinel: Searching for failed authentication attempts...
[Calls hunt_by_timeframe with attack_types=["brute_force"]]

Found 47 failed login attempts from 3 source IPs targeting the "admin" account.
Top sources:
- 192.168.1.105: 28 attempts
- 10.0.0.42: 15 attempts
- 172.16.0.8: 4 attempts
```

### Example 2: Investigate a Suspicious Host

```
You: Show me all activity on host DESKTOP-ABC123 in the last 24 hours

CrowdSentinel: Generating a forensic timeline for that host...
[Calls get_host_activity_timeline]

Timeline shows:
- 09:15: User "jsmith" logged in (Event 4624)
- 09:17: PowerShell executed encoded command
- 09:18: New scheduled task created "WindowsUpdate"
- 09:22: Outbound connection to 203.0.113.42:443
- 09:25: LSASS memory access detected
```

### Example 3: Kill Chain Analysis

```
You: We found C2 beaconing. What should we hunt for next?

CrowdSentinel: Hunting adjacent kill chain stages...
[Calls hunt_adjacent_stages with current_stage="COMMAND_AND_CONTROL"]

Looking backwards (Installation stage):
- Found scheduled task persistence on 3 hosts
- Registry Run key modifications detected

Looking forwards (Actions on Objectives):
- Lateral movement to 2 additional hosts via SMB
- Credential dumping attempts detected
```

### Example 4: Network Traffic Analysis

```
You: Analyse this PCAP for C2 beaconing

CrowdSentinel: Checking for regular connection intervals...
[Calls detect_beaconing on the PCAP file]

Detected beaconing pattern:
- Host: 192.168.1.50 → 203.0.113.100:443
- Interval: 60 seconds (±2s jitter)
- Duration: 4 hours
- Confidence: HIGH

Recommend blocking 203.0.113.100 and investigating 192.168.1.50.
```

### Example 5: CLI Threat Hunt

```bash
# Hunt for encoded PowerShell
crowdsentinel hunt "powershell -enc" -i winlogbeat-* --timeframe 1440 -o json

# Pipe results to analysis
crowdsentinel hunt "event.code:4625" -i winlogbeat-* -o json | \
  crowdsentinel analyse -c "Failed authentication investigation"

# Search detection rules for lateral movement
crowdsentinel rules --tactic lateral_movement -p windows
```

---

## Compatibility

| Package | Backend | Install |
|:--------|:--------|:--------|
| `crowdsentinel-mcp-server` | Elasticsearch 8.x (default) | `pip install crowdsentinel-mcp-server` |
| `crowdsentinel-mcp-server-es7` | Elasticsearch 7.x | `pip install crowdsentinel-mcp-server-es7` |
| `crowdsentinel-mcp-server-es9` | Elasticsearch 9.x | `pip install crowdsentinel-mcp-server-es9` |
| `opensearch-mcp-server` | OpenSearch 1.x, 2.x, 3.x | `pip install opensearch-mcp-server` |

---

## For Developers

<details>
<summary>Project Structure</summary>

```
crowdsentinel-mcp-server/
├── src/
│   ├── server.py                 # MCP server entry point
│   ├── version.py                # Version constant
│   ├── risk_config.py            # Write operation controls
│   ├── transport_security.py     # Origin validation for HTTP transports (anti DNS-rebinding)
│   ├── transport_audit.py        # Transport-level audit logging (every HTTP exchange)
│   │
│   ├── cli/                      # Standalone CLI
│   │   └── main.py               # CLI entry point (argparse) — 15 commands incl. doctor
│   │
│   ├── agent/                    # `analyse --mcp` AI agent mode (multi-provider LLM auth)
│   ├── config/                   # Connector configuration
│   │
│   ├── clients/                  # Backend logic layer
│   │   ├── base.py               # Base client, authentication
│   │   ├── exceptions.py         # Exception handling decorators
│   │   └── common/
│   │       ├── client.py         # Unified SearchClient (multiple inheritance)
│   │       ├── threat_hunting.py # Threat hunting queries
│   │       ├── ioc_analysis.py   # IoC extraction & analysis
│   │       ├── deobfuscate.py    # Encoded-command decoding (stdlib core + optional chepy)
│   │       ├── cyber_kill_chain.py # Kill chain logic
│   │       ├── rule_loader.py    # Detection rule loading
│   │       ├── chainsaw_client.py # EVTX/Sigma integration
│   │       ├── osquery_client.py # Local osquery execution (sqlglot-validated SQL)
│   │       ├── misp_client.py    # MISP export/search
│   │       ├── threat_intel.py   # Shodan/VirusTotal/AbuseIPDB/ThreatFox enrichment
│   │       └── schemas/          # Data-driven schema registry
│   │           ├── ecs.py, sysmon.py, windows_security.py, auditd.py
│   │           └── defs/         # JSON schema defs (zeek, packetbeat, aws_cloudtrail, …)
│   │
│   ├── tools/                    # MCP tool interfaces (25 modules, 139 tools)
│   │   ├── register.py           # Dynamic tool registration
│   │   ├── threat_hunting.py     # Hunting tool definitions
│   │   ├── rule_management.py    # Rule management tools
│   │   ├── velociraptor_tools.py # Live endpoint forensics (25 tools)
│   │   ├── osquery_tools.py      # Local host forensics (4 tools)
│   │   ├── cross_correlation.py  # SIEM ↔ endpoint correlation (5 tools)
│   │   ├── chainsaw_hunting.py   # Chainsaw tools
│   │   ├── wireshark_tools.py    # Network analysis tools
│   │   ├── threat_intel.py       # Enrichment + MISP tools
│   │   └── investigation_state_tools.py # State management tools
│   │
│   ├── storage/                  # Persistent investigation state
│   │   ├── investigation_state.py # Core state management
│   │   ├── storage_manager.py    # File system storage (8GB FIFO)
│   │   └── models.py             # Pydantic models (IoC, Investigation)
│   │
│   ├── utils/                    # Shared utilities
│   │
│   └── wireshark/                # Network traffic analysis
│       ├── core/                 # TShark execution, PCAP parsing
│       ├── hunting/              # Beaconing, lateral movement, IoC hunting
│       ├── baseline/             # Traffic baseline creation
│       ├── extraction/           # File carving from traffic
│       └── reporting/            # NCSC-style reports, timelines
│
├── rules/                        # 6,060 detection rules (EQL + Lucene)
├── chainsaw/                     # Chainsaw binary + 3,000+ Sigma rules
├── skills/                       # Claude Code agent skills
├── Makefile                      # Test pyramid + release automation
└── tests/                        # Tiered test suite (unit / integration / api / e2e / system)
```

</details>

<details>
<summary>Design Patterns</summary>

| Pattern | Usage |
|:--------|:------|
| **Multiple Inheritance** | `SearchClient` composes all specialised clients |
| **Decorator** | Exception handling via `@handle_exceptions` |
| **Factory** | `create_search_client()` creates appropriate client |
| **Plugin Architecture** | Tools registered dynamically via `ToolsRegister` |
| **Auto-Capture** | Tool results automatically analysed for IoCs |

</details>

<details>
<summary>Adding a New Tool</summary>

1. **Create client method** in `src/clients/common/your_module.py`:
```python
class YourClient(SearchClientBase):
    def your_method(self, param: str) -> dict:
        # Implementation
        return results
```

2. **Add to SearchClient** in `src/clients/common/client.py`:
```python
class SearchClient(YourClient, OtherClients, ...):
    pass
```

3. **Create tool wrapper** in `src/tools/your_tools.py`:
```python
class YourTools:
    def __init__(self, client, mcp):
        self.client = client
        self.mcp = mcp

def register_tools(self):
        @self.mcp.tool()
        def your_tool(param: str) -> str:
            """Tool description for LLM."""
            result = self.client.your_method(param)
            return json.dumps(result)
```

4. **Register in server** in `src/server.py`:
```python
from src.tools.your_tools import YourTools

def _register_tools(self):
    # ... existing tools ...
    YourTools(self.client, self.mcp).register_tools()
```

</details>

<details>
<summary>Running Tests</summary>

The test suite is a bottom-up pyramid (see `tests/README.md`): hermetic unit tests, then live tiers that spin up a real Elasticsearch (via [testcontainers](https://testcontainers-python.readthedocs.io/)) and the real MCP server.

```bash
make test-unit          # fast hermetic loop (default developer command)
make coverage           # unit tier + coverage policy gate
make check-tests        # policy: every new function vs origin/main has a test
make test-integration   # real ES via testcontainers (Docker required)
make test-api           # + real MCP server subprocess over streamable-http
make test-e2e           # + real MCP client journey over the wire
make test-suite         # the whole pyramid, bottom-up, with a summary table
```

| Tier | What it proves | Backing services |
|:-----|:---------------|:-----------------|
| Unit | Function-level behaviour, fail-fast validation | None (hermetic) |
| Integration | App ↔ Elasticsearch trust boundary (auth, TLS, seeded data) | Real ES via testcontainers |
| API | MCP-over-HTTP contract (schemas, errors, Origin security, audit logs) | Real ES + real server subprocess |
| E2E | Full analyst journey via a real MCP client | Real ES + real server + `fastmcp.Client` |
| System | Full pipeline against your own range cluster | BYO Elasticsearch |

Live tiers are opt-in (`--run-integration` / `--run-api` / `--run-e2e` / `--run-system`), so plain `pytest tests/` stays fast and hermetic.

</details>

<details>
<summary>Local Testing Environment</summary>

```bash
# Start Elasticsearch
docker-compose -f docker-compose-elasticsearch.yml up -d

# Start OpenSearch
docker-compose -f docker-compose-opensearch.yml up -d
```

**Default credentials (testing only):**
- Elasticsearch: `elastic` / `test123`
- OpenSearch: `admin` / `admin`

</details>

---

## Roadmap

| Feature | Status | Description |
|:--------|:------:|:------------|
| **Velociraptor Integration** | **Done** | 25 live endpoint forensics tools + 5 cross-correlation tools via the Velociraptor API |
| **osquery Integration** | **Done** | SQL-based local host forensics (processes, sockets, users, ad-hoc queries) |
| **Encoded-Command Deobfuscation** | **Done** | Recover IoCs hidden in base64/UTF-16LE/gzip/hex-encoded commands (optional chepy for the long tail) |
| **Threat Intel Enrichment** | **Done** | IoC enrichment via Shodan InternetDB, VirusTotal, AbuseIPDB, ThreatFox + STIX 2.1 export |
| **MISP Integration** | **Done** | Export investigation IoCs as MISP events, search MISP attributes (offline JSON export without a server) |
| **Zeek Integration** | Partial | Zeek logs indexed into ES are hunted via the data-driven schema registry; native NSM integration planned |
| **Wazuh Integration** | Planned | Open-source EDR/XDR — its indexer is OpenSearch-based, so CrowdSentinel's existing OpenSearch client can hunt Wazuh alerts and agent telemetry |
| **Splunk Integration** | Planned | Add Splunk as a data source alongside Elasticsearch |
| **Sigma Rule Converter** | Planned | Convert Sigma rules to native ES/Splunk queries |
| **Case Management** | Planned | Export investigations to TheHive, JIRA |
| **Custom Rule Builder** | Planned | Create detection rules via natural language |

See [CHANGELOG.md](CHANGELOG.md) for detailed version history.

---

## Velociraptor Integration (Live Endpoint Forensics)

CrowdSentinel integrates with [Velociraptor](https://docs.velociraptor.app/) for live endpoint forensic artefact collection. When configured, 25 additional MCP tools and 5 cross-correlation tools become available.

### Setup

```bash
# Install optional dependencies
pip install crowdsentinel-mcp-server[velociraptor]

# Set the Velociraptor API config path
export VELOCIRAPTOR_API_CONFIG="/path/to/api_client.yaml"
```

The API client config is generated from the Velociraptor server:
```bash
velociraptor config api_client --name crowdsentinel --role administrator,api \
  --config server.config.yaml /path/to/api_client.yaml
```

### Available Tools

| Category | Tools | Use Case |
|:---------|:------|:---------|
| **Discovery** | `velociraptor_client_info`, `velociraptor_list_clients`, `velociraptor_list_artifacts` | Resolve hostnames, enumerate enrolled endpoints, discover available artefacts |
| **Generic Collection** | `velociraptor_collect_artifact`, `velociraptor_get_collection_results` | Collect any Velociraptor artefact and fetch its results |
| **Live State** | `velociraptor_pslist`, `velociraptor_netstat`, `velociraptor_users`, `velociraptor_groups`, `velociraptor_mounts` | Running processes, active network connections, accounts, groups, mounted volumes |
| **Execution Evidence** | `velociraptor_prefetch`, `velociraptor_amcache`, `velociraptor_shimcache`, `velociraptor_userassist`, `velociraptor_bam`, `velociraptor_srum` | Forensic proof of programme execution and resource usage |
| **Persistence** | `velociraptor_services`, `velociraptor_scheduled_tasks`, `velociraptor_autoruns` | Service, scheduled task, and autorun persistence mechanisms |
| **User Activity** | `velociraptor_shellbags`, `velociraptor_recentdocs`, `velociraptor_lnk`, `velociraptor_evidence_of_download` | User browsing, document access, link files, file downloads |
| **Filesystem & Logs** | `velociraptor_ntfs_mft`, `velociraptor_evtx` | MFT search by name/path/timestamp, remote EVTX queries |
| **Cross-Correlation** | `correlate_siem_with_endpoint`, `endpoint_to_siem_pivot`, `endpoint_hunt_from_ioc`, `correlate_by_time`, `build_unified_timeline` | Validate SIEM findings on endpoints, pivot from endpoint IoCs to fleet-wide SIEM searches, unified timelines |

### Cross-Source IoC Sharing

IoCs extracted from Velociraptor artefacts are automatically captured into the active investigation alongside SIEM, Chainsaw, and Wireshark findings. Use `get_shared_iocs` to retrieve the combined indicator set for cross-source correlation.

```
SIEM (Elasticsearch)          Endpoint (Velociraptor)
       │                              │
  hunt_by_timeframe()         velociraptor_pslist()
       │                              │
  auto_capture ──────► Investigation State ◄────── auto_capture
                              │
                     get_shared_iocs()
```

### DFIR Knowledge Resources

9 MCP resources provide structured investigation reference data directly to connected AI agents:

| Resource | Content |
|:---------|:--------|
| `crowdsentinel://investigation-workflow` | Mandatory 4-phase IR workflow |
| `crowdsentinel://ioc-reference` | IoC types ranked by Pyramid of Pain |
| `crowdsentinel://ioc-reference/data` | Machine-readable IoC reference data |
| `crowdsentinel://cross-correlation-playbooks` | 5 investigation playbooks (suspicious process, brute force, lateral movement, persistence, exfiltration) |
| `crowdsentinel://velociraptor-guide` | Artefact reference tables and "found X in SIEM → check Y on endpoint" decision tree |
| `crowdsentinel://data-sources` | All data source capabilities and investigation decision matrix |
| `crowdsentinel://tool-recommendations` | Which tool to reach for at each investigation step |
| `crowdsentinel://schemas` | Supported log-source schemas (ECS, Sysmon, Windows Security, auditd, Zeek, …) |
| `crowdsentinel://schemas/list` | Machine-readable schema listing |

---

<a name="documentation"></a>
## Documentation

### User Guides

| Document | Description |
|:---------|:------------|
| [FIRST_TIME_SETUP.md](FIRST_TIME_SETUP.md) | Detailed first-time setup instructions |
| [HOW_TO_USE.md](HOW_TO_USE.md) | Comprehensive usage guide |
| [QUICK_START.md](QUICK_START.md) | 5-minute quick start |
| [TRANSPORT_MODES.md](TRANSPORT_MODES.md) | stdio, SSE, HTTP configuration |

### Feature Guides

| Document | Description |
|:---------|:------------|
| [THREAT_HUNTING_GUIDE.md](THREAT_HUNTING_GUIDE.md) | Threat hunting workflows |
| [DETECTION_RULES_GUIDE.md](DETECTION_RULES_GUIDE.md) | Using 6,060 detection rules |
| [CYBER_KILL_CHAIN_GUIDE.md](CYBER_KILL_CHAIN_GUIDE.md) | Kill chain analysis |
| [CHAINSAW_GUIDE.md](CHAINSAW_GUIDE.md) | EVTX log analysis with Sigma |
| [INVESTIGATION_PROMPTS_GUIDE.md](INVESTIGATION_PROMPTS_GUIDE.md) | Fast triage spine |
| [AI_AGENT_INTEGRATION.md](AI_AGENT_INTEGRATION.md) | Workflow guidance for AI agents |

### Developer Guides

| Document | Description |
|:---------|:------------|
| [ARCHITECTURE.md](ARCHITECTURE.md) | Detailed architecture documentation |
| [CONTRIBUTING.md](CONTRIBUTING.md) | Contribution guidelines |

---

## Contributing

Contributions are welcome! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

---

## Licence

GNU General Public Licence v3.0 — See [LICENSE](LICENSE) for details.

---

## Cyber Range

CrowdSentinel ships with a companion **[crowdsentinel-range](https://github.com/thomasxm/crowdsentinel-range)** — a fully ephemeral AWS lab that generates ground-truth-labeled attack telemetry so you can investigate real detections rather than synthetic data.

### Current range (v1) — 2-host AWS lab

```
┌──────────────────────────── AWS VPC (private subnet) ────────────────────────────────┐
│                                                                                        │
│  ┌──────────────────────────────┐      ┌──────────────────────────────────────────┐  │
│  │   Linux SIEM (Ubuntu 22.04)  │      │   Windows Range Box (Server 2022)        │  │
│  │   Elasticsearch 8.x (TLS)   │◄─────│   Sysmon (olafhartong) + Winlogbeat 9    │  │
│  │   Auditbeat + Filebeat       │      │   Atomic Red Team + PurpleSharp          │  │
│  └──────────────────────────────┘      └──────────────────────────────────────────┘  │
│                         SSM VPC endpoints — no inbound ports open                     │
└───────────────────────────────────────┬────────────────────────────────────────────--┘
                                         │ SSM port-forward :19200
                              ┌──────────▼──────────────────────┐
                              │  ./range-mcp.sh → CrowdSentinel │
                              │  MCP Server → Claude Code       │
                              └─────────────────────────────────┘
```

**3 commands to go from zero to hunting:**
```bash
cd crowdsentinel-range && make up && make attack-windows
cd .. && ./range-mcp.sh
# then in Claude Code: /mcp → "investigate potential intrusions on the windows machine"
```

> Demo: [73,328 events triaged in ~40 seconds](https://github.com/thomasxm/crowdsentinel-range/blob/main/docs/demo-windows-triage-investigation.md) — 2 shellcode payloads decoded, C2 IP extracted from raw bytes, full IR report with 19 MITRE techniques.

---

### Future range (v2) — enterprise AD environment

The next range generation targets **full Active Directory kill-chain coverage**: initial access → lateral movement → domain compromise, with a network security monitor layer, runtime security instrumentation, centralised vulnerability management, and deception infrastructure. Inspired by [DetectionLab](https://github.com/clong/DetectionLab), [Ludus](https://docs.ludus.cloud/), and [SimuLand](https://github.com/Azure/SimuLand).

```
┌───────────────────────────────────── AWS / Multi-VPC ───────────────────────────────────────────────────┐
│                                                                                                           │
│  ┌──── Attacker Subnet ────┐   ┌───────────── Corporate Subnet ──────────────────────────────────────┐  │
│  │                          │   │                                                                       │  │
│  │  Kali Linux (C2 server)  │   │  ┌─────────────────┐  ┌──────────────────┐  ┌──────────────────┐  │  │
│  │  Caldera + Metasploit    │   │  │  Domain          │  │  Windows 11      │  │  Windows 11      │  │  │
│  │  Covenant C2             │──▶│  │  Controller      │  │  Workstation 1   │  │  Workstation 2   │  │  │
│  │                          │   │  │  (AD DS, DNS)    │  │  (domain-joined) │  │  (domain-joined) │  │  │
│  └──────────────────────────┘   │  └─────────────────┘  └──────────────────┘  └──────────────────┘  │  │
│                                  │  ┌──────────────────────────────────────────────────────────────┐  │  │
│  ┌──── DMZ Subnet ─────────┐    │  │   Linux File/Web Server (IIS / Apache, SMB share)            │  │  │
│  │                          │    │  └──────────────────────────────────────────────────────────────┘  │  │
│  │  Nginx reverse proxy     │    └───────────────────────────────────────────────────────────────────┘  │
│  │  Simulated internet SVC  │                                                                            │
│  └──────────────────────────┘   ┌───────────── Management / SIEM Subnet ──────────────────────────┐    │
│                                  │                                                                   │    │
│                                  │  ┌─────────────────────┐   ┌───────────────────────────────┐   │    │
│                                  │  │  Elasticsearch +     │   │  Zeek / Suricata              │   │    │
│                                  │  │  Kibana (SIEM)       │   │  (NSM — full packet + alerts) │   │    │
│                                  │  └─────────────────────┘   └───────────────────────────────┘   │    │
│                                  │  ┌─────────────────────┐   ┌───────────────────────────────┐   │    │
│                                  │  │  Velociraptor        │   │  Falco (runtime security)     │   │    │
│                                  │  │  (live EDR/forensics)│   │  eBPF probe (CO-RE, default)  │   │    │
│                                  │  └─────────────────────┘   │  + kernel module fallback     │   │    │
│                                  │  ┌─────────────────────┐   └───────────────────────────────┘   │    │
│                                  │  │  DefectDojo          │   ┌───────────────────────────────┐   │    │
│                                  │  │  (vuln management)   │   │  Honeypots + Canary tokens     │   │    │
│                                  │  │  Falco·Zeek·scanners │   │  (deception layer)             │   │    │
│                                  │  └─────────────────────┘   └───────────────────────────────┘   │    │
│                                  │  ┌─────────────────────────────────────────────────────────┐   │    │
│                                  │  │  Grafana — centralized dashboards + alerting             │   │    │
│                                  │  │  ES · Falco · Suricata · Velociraptor · DefectDojo       │   │    │
│                                  │  └─────────────────────────────────────────────────────────┘   │    │
│                                  └───────────────────────────────────────────────────────────────┘    │
│                                         VyOS router — inter-subnet ACLs + egress filter               │
└───────────────────────────────────────────────────────────────────────────────────────────────────────┘
                                                  │ SSM / VPN
                                    CrowdSentinel MCP + Claude Code
```

**v2 target capabilities:**

| Capability | v1 (current) | v2 (planned) |
|------------|-------------|--------------|
| Hosts | 2 (Linux SIEM + Windows) | 7–10 (DC + 2× WS + Linux + NSM + attacker + SIEM) |
| Network segments | 1 (private subnet) | 4 (attacker / corp / DMZ / management) |
| Active Directory | — | Full AD DS domain + GPO + Kerberos |
| Lateral movement coverage | Limited | Pass-the-Hash, Kerberoasting, DCSync |
| Network detection | — | Zeek (NSM) + Suricata IDS |
| Runtime security | — | Falco; modern eBPF probe (CO-RE, bundled, default) + kernel module fallback; syscall-level host + container detection |
| Endpoint forensics | — | Velociraptor live triage |
| Vuln management | — | DefectDojo; aggregates Falco alerts, Zeek/Suricata findings, scanner results (OpenVAS, Trivy) into unified tracking + remediation workflow |
| Dashboards | — | Grafana; centralised metrics + alert visualisation across ES, Falco, Suricata, Velociraptor, and DefectDojo |
| Deception layer | — | Honeypot + canary tokens |
| C2 infrastructure | ART atomics only | Caldera + Metasploit + Covenant |
| Attack scenarios | Windows atomics + EVTX replay | Full kill-chain: initial access → domain compromise |
| CrowdSentinel coverage | ES hunt + IR | ES + Zeek/Suricata + Falco + Velociraptor cross-source correlation; DefectDojo/Grafana as upstream context |

**Design references:** [DetectionLab](https://github.com/clong/DetectionLab) (Sysmon+WEF+Splunk convergence), [Ludus](https://docs.ludus.cloud/) (modular Proxmox/Ansible, VLAN segmentation), [SimuLand](https://github.com/Azure/SimuLand) (multi-domain AD forest, cloud-native), [SANS FOR508](https://www.sans.org/cyber-security-courses/advanced-incident-response-threat-hunting-training/) (artifact-first DFIR workflow), [Falco](https://falco.org/docs/concepts/falco-kernel-testing/) (CO-RE eBPF probe architecture, kernel module fallback).

## Acknowledgements

CrowdSentinel stands on the shoulders of outstanding open-source projects. Thank you to all of their maintainers and contributors.

**Protocol & server framework**

- [Model Context Protocol](https://modelcontextprotocol.io/) — the protocol connecting LLMs to tools, by Anthropic
- [FastMCP](https://github.com/jlowin/fastmcp) — the Python MCP server framework this project is built on

**Analysis engines & forensic tools**

- [Chainsaw](https://github.com/WithSecureLabs/chainsaw) — EVTX log analyser by WithSecure Labs
- [Velociraptor](https://docs.velociraptor.app/) — live endpoint forensics and DFIR platform by Velocidex/Rapid7
- [osquery](https://osquery.io/) — SQL-powered host instrumentation by the osquery Foundation
- [Wireshark / TShark](https://www.wireshark.org/) — network protocol analysis by the Wireshark Foundation
- [Chepy](https://github.com/securisec/chepy) — CyberChef-like decoding library powering optional long-tail deobfuscation
- [sqlglot](https://github.com/tobymao/sqlglot) — SQL parser used to safely validate osquery queries

**Detection content**

- [Sigma / SigmaHQ](https://github.com/SigmaHQ/sigma) — the community detection rule standard and rule corpus
- [Elastic detection-rules](https://github.com/elastic/detection-rules) — Elastic's prebuilt EQL/ES|QL detection rules
- Community-contributed Sigma and custom rules

**Data platforms & threat intelligence**

- [Elasticsearch](https://github.com/elastic/elasticsearch-py) and [OpenSearch](https://github.com/opensearch-project/opensearch-py) Python clients
- [MISP / PyMISP](https://github.com/MISP/PyMISP) — open-source threat intelligence platform and client
- [stix2](https://github.com/oasis-open/cti-python-stix2) — OASIS STIX 2.1 library for structured IoC export
- [Shodan InternetDB](https://internetdb.shodan.io/), [VirusTotal](https://www.virustotal.com/), [AbuseIPDB](https://www.abuseipdb.com/), and [abuse.ch ThreatFox](https://threatfox.abuse.ch/) — IoC enrichment services with free tiers

**Development & testing**

- [testcontainers-python](https://github.com/testcontainers/testcontainers-python) — real Elasticsearch containers for the live test tiers
- [pytest](https://pytest.org/), [Ruff](https://github.com/astral-sh/ruff), [Bandit](https://github.com/PyCQA/bandit) — test runner, linting, and SAST

**Methodology frameworks**

- Cyber Kill Chain (Lockheed Martin), Pyramid of Pain (David J. Bianco), Diamond Model (Caltagirone, Pendergast & Betz), [MITRE ATT&CK](https://attack.mitre.org/)

---

**Made for the security community by [medjedtxm](https://github.com/thomasxm)**

[![GitHub](https://img.shields.io/badge/GitHub-CrowdSentinel-181717?style=for-the-badge&logo=github)](https://github.com/thomasxm/CrowdSentinels-AI-MCP)
[![PyPI](https://img.shields.io/badge/PyPI-crowdsentinel--mcp--server-3775A9?style=for-the-badge&logo=pypi&logoColor=white)](https://pypi.org/project/crowdsentinel-mcp-server/)

</div>

CrowdSentinels-AI-MCP

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README