Threat Hunting
A minimal, modular MCP server that equips your AI with practical capabilities for real-world threat hunting workflows.
What is Threat Hunting?
Threat Hunting is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to minimal, modular mcp server that equips your ai with practical capabilities for real-world threat hunting workflows.
A minimal, modular MCP server that equips your AI with practical capabilities for real-world threat hunting workflows.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A minimal, modular MCP server that equips your AI with pract
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx threat-huntingConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Threat Hunting
The Threat Hunting MCP Server equips AI assistants with a modular, practical toolkit for real-world security threat hunting workflows, integrating MITRE ATT&CK techniques, the PEAK threat hunting framework, and the community HEARTH hunt hypothesis library. It exposes over 20 tools for generating behavioral hunt reports, converting IOCs to TTP-focused detections, querying community hunts, analyzing adversary behavior, and integrating with Splunk for live query execution. Security analysts and blue team practitioners use it to accelerate hypothesis generation, standardize hunt documentation, and leverage community knowledge directly from their AI assistant.
Prerequisites
- Python 3.11–3.13 installed
- Git to clone the repository and optionally the HEARTH community hunts repository
- Optional: Splunk SDK (pip install splunk-sdk) for Splunk integration
- Optional: Atlassian account and API token for Jira/Confluence integration
- An MCP-compatible client (Claude Desktop, Claude Code)
Clone the repository
Clone the threat-hunting-mcp-server repository and optionally the HEARTH community hunt library as a sibling directory.
git clone https://github.com/THORCollective/threat-hunting-mcp-server
cd threat-hunting-mcp-server
# Optional: clone HEARTH community hunts
git clone https://github.com/THORCollective/HEARTH ../HEARTHInstall dependencies
Install the base Python requirements. Optional packages for Splunk, ML analysis, and NLP can be added as needed.
pip install -r requirements.txt
# Optional extras:
pip install splunk-sdk
pip install numpy pandas scikit-learn
pip install spacy && python -m spacy download en_core_web_lgConfigure environment variables
Copy .env.example to .env and fill in the credentials for any integrations you want enabled. All integrations are optional and degrade gracefully if not configured.
cp .env.example .env
# Edit .env and set as needed:
# HEARTH_PATH=/path/to/HEARTH
# SPLUNK_HOST=your-splunk-host
# SPLUNK_PORT=8089
# SPLUNK_TOKEN=your-token
# ATLASSIAN_URL=https://your-org.atlassian.net
# [email protected]
# ATLASSIAN_API_TOKEN=your-api-tokenStart the MCP server
Run the server module directly with Python. It will start in stdio mode ready for MCP client connections.
python -m src.serverConfigure your MCP client
Add the threat hunting server to your Claude Desktop or Claude Code configuration.
Threat Hunting Examples
Client configuration
Claude Desktop configuration for the Threat Hunting MCP server. Replace /path/to/threat-hunting-mcp-server with your actual clone path.
{
"mcpServers": {
"threat-hunting": {
"command": "python3",
"args": ["-u", "/path/to/threat-hunting-mcp-server/src/server.py"]
}
}
}Prompts to try
Example prompts using MITRE ATT&CK technique IDs, PEAK framework hunts, and HEARTH community hunts.
- "Hunt for any process accessing LSASS memory (T1003.001)"
- "Create a behavioral hunt report for lateral movement via remote execution T1021"
- "Show me HEARTH community hunts for credential access techniques"
- "Convert this IOC to a TTP-focused detection: malicious PowerShell downloading from pastebin"
- "Analyze the adversary behavior pattern in this incident and suggest hunt hypotheses"
- "Recommend threat hunts suitable for a Windows Active Directory environment"Troubleshooting Threat Hunting
Community hunt tools return no results or HEARTH tools are unavailable
Ensure the HEARTH_PATH environment variable in your .env file points to the correct absolute path of the HEARTH repository clone. Run 'get_server_health' tool to check which features are enabled.
Splunk integration tools fail with connection errors
Verify SPLUNK_HOST, SPLUNK_PORT, and SPLUNK_TOKEN are set correctly in .env. Confirm the Splunk REST API port (default 8089) is reachable from your machine. Install splunk-sdk with 'pip install splunk-sdk' if not already installed.
The server fails to start with ModuleNotFoundError
Make sure you installed requirements from the correct directory ('pip install -r requirements.txt' inside the threat-hunting-mcp-server folder). Use a virtual environment to avoid package conflicts with other Python projects.
Frequently Asked Questions about Threat Hunting
What is Threat Hunting?
Threat Hunting is a Model Context Protocol (MCP) server that minimal, modular mcp server that equips your ai with practical capabilities for real-world threat hunting workflows. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Threat Hunting?
Follow the installation instructions on the Threat Hunting GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Threat Hunting?
Threat Hunting works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Threat Hunting free to use?
Yes, Threat Hunting is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Threat Hunting Alternatives — Similar Security Servers
Looking for alternatives to Threat Hunting? 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 Threat Hunting 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 Threat Hunting?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.