Security Investigator
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-instructions.
What is Security Investigator?
Security Investigator is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to automated security investigation tool using microsoft mcp servers, github copilot, python modules and custom copilot-instructions.
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-instructions.
This server falls under the Security and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Automated security investigation tool using Microsoft MCP Se
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx security-investigatorConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Security Investigator
Security Investigator is an automated security investigation system that wires together Microsoft Sentinel, Microsoft Defender, Microsoft Graph, KQL Search, and Python-based threat intel modules under GitHub Copilot's MCP framework. It provides 25 pre-built investigation skills — covering threat pulse scans, user and incident investigations, identity posture analysis, geospatial visualization, and detection authoring — and is designed for security operations teams that want AI-assisted, end-to-end incident response within VS Code.
Prerequisites
- VS Code 1.99 or higher with a GitHub Copilot Pro+, Business, or Enterprise subscription
- Python 3.8 or higher and Node.js 18 or higher
- Azure CLI installed with the log-analytics extension ('az extension add --name log-analytics')
- Microsoft Sentinel workspace with valid workspace ID, tenant ID, and subscription ID
- API keys for threat intel services: IPINFO_TOKEN, ABUSEIPDB_TOKEN, and optionally SHODAN_TOKEN and VPNAPI_TOKEN
Clone the repository
Clone the security-investigator repository and open it in VS Code.
git clone https://github.com/SCStelz/security-investigator.git
code security-investigatorSet up the Python environment
Create a virtual environment and install Python dependencies.
python -m venv .venv
.venv\Scripts\Activate.ps1
pip install -r requirements.txtCopy and fill in configuration files
Copy all three template files and populate them with your Azure and threat intel credentials.
copy config.json.template config.json
copy .env.template .env
copy .vscode\mcp.json.template .vscode\mcp.jsonConfigure config.json with your Sentinel workspace
Edit config.json to add your Microsoft Sentinel workspace ID, tenant ID, subscription ID, and resource group.
{
"sentinel_workspace_id": "YOUR_WORKSPACE_ID_HERE",
"tenant_id": "YOUR_TENANT_ID_HERE",
"subscription_id": "YOUR_SUBSCRIPTION_ID_HERE",
"azure_mcp": {
"resource_group": "YOUR_RESOURCE_GROUP",
"workspace_name": "YOUR_WORKSPACE_NAME",
"tenant": "YOUR_TENANT_ID",
"subscription": "YOUR_SUBSCRIPTION_ID"
},
"output_dir": "reports"
}Set threat intel API keys in .env
Add your API keys for IP reputation and geolocation services to the .env file.
IPINFO_TOKEN=your_ipinfo_token
ABUSEIPDB_TOKEN=your_abuseipdb_token
VPNAPI_TOKEN=your_vpnapi_token
SHODAN_TOKEN=your_shodan_tokenLog in to Azure and verify connectivity
Authenticate with Azure CLI so the MCP servers can query Sentinel and Defender on your behalf.
az login
az account set --subscription YOUR_SUBSCRIPTION_IDSecurity Investigator Examples
Client configuration
VS Code mcp.json configuration block for the Security Investigator MCP server.
{
"mcpServers": {
"security-investigator": {
"command": "python",
"args": ["-m", "security_investigator"],
"env": {
"IPINFO_TOKEN": "your_ipinfo_token",
"ABUSEIPDB_TOKEN": "your_abuseipdb_token",
"VPNAPI_TOKEN": "your_vpnapi_token",
"SHODAN_TOKEN": "your_shodan_token"
}
}
}
}Prompts to try
Example prompts that invoke Security Investigator's built-in investigation skills.
- "Run a threat pulse scan on our Sentinel workspace"
- "Investigate user [email protected] for the last 7 days"
- "Analyze incident 12345 and give me a triage summary"
- "Is IP address 203.0.113.42 malicious? Check reputation across all threat intel sources"
- "Generate an email threat protection report for the last 30 days"
- "Create a KQL detection rule for brute force login attempts"Troubleshooting Security Investigator
Azure CLI authentication errors or 'Unauthorized' when querying Sentinel
Run 'az login' and 'az account set --subscription YOUR_SUBSCRIPTION_ID' to refresh your credentials. Ensure your account has at least the 'Microsoft Sentinel Reader' role on the Sentinel workspace.
Threat intel API calls return 401 or quota exceeded
Verify IPINFO_TOKEN, ABUSEIPDB_TOKEN, and other keys in the .env file are correct. Free tiers have daily request limits — upgrade your plan or rotate to a new token if you have exceeded the quota.
Python module import errors or missing dependencies
Ensure you have activated the virtual environment (.venv\Scripts\Activate.ps1 on Windows or 'source .venv/bin/activate' on macOS/Linux) and that 'pip install -r requirements.txt' completed without errors.
Frequently Asked Questions about Security Investigator
What is Security Investigator?
Security Investigator is a Model Context Protocol (MCP) server that automated security investigation tool using microsoft mcp servers, github copilot, python modules and custom copilot-instructions. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Security Investigator?
Follow the installation instructions on the Security Investigator GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Security Investigator?
Security Investigator works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Security Investigator free to use?
Yes, Security Investigator is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Security Investigator Alternatives — Similar Security Servers
Looking for alternatives to Security Investigator? Here are other popular security servers you can use with Claude, Cursor, and VS Code.
Casdoor
★ 13.6kAn open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD
ghidraMCP
★ 9.0kAn Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through
HexStrike AI
★ 8.9kHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b
IDA Pro MCP
★ 8.7kEnables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.
Anthropic Cybersecurity Skills
★ 6.6k754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform
Hooker
★ 5.1k🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u
Browse More Security MCP Servers
Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Security Investigator in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Security Investigator?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.