Litterbox
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
What is Litterbox?
Litterbox is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to self-hosted sandbox for red teams to test payloads against modern detection before deployment. mcp integration lets an llm agent drive analysis end to end.
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A self-hosted sandbox for red teams to test payloads against
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx litterboxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Litterbox
LitterBox is a self-hosted payload-analysis sandbox designed for red teams who need to test offensive security payloads against modern endpoint detection before deploying them in the field. It runs static analysis, dynamic analysis, and EDR-instrumented scanning (via Elastic Defend or Fibratus on a Windows VM) against uploaded samples, producing a Detection Score and a breakdown of triggering indicators. The integrated MCP server — called LitterBoxMCP — lets an LLM agent drive the full analysis pipeline end to end, from uploading a payload to interpreting results, without manual dashboard interaction.
Prerequisites
- Python 3.11 or later with an admin/root shell
- Windows 10/11 for native installation (Linux is supported via Docker with KVM for the Windows analysis VM)
- Docker and Docker Compose for the Linux deployment path (initial build takes approximately one hour)
- An MCP-compatible AI client such as Claude Desktop or Claude Code
- Optional: Elastic Defend or Fibratus installed on a separate EDR-instrumented Windows VM for live EDR scanning
Clone the repository
Clone the LitterBox repository to your analysis machine. This includes the main application, scanner binaries, YARA rules, Docker setup, and EDR profile configuration.
git clone https://github.com/BlackSnufkin/LitterBox.git
cd LitterBoxInstall on Windows (native)
On Windows, create a Python virtual environment, install dependencies, and start the server. Run from an administrator PowerShell session.
python -m venv venv
.\venv\Scripts\Activate.ps1
pip install -r requirements.txt
python litterbox.pyInstall on Linux (Docker with Windows KVM)
On Linux, use the Docker setup script. It provisions a Windows 10 KVM container and installs LitterBox inside. The initial build takes roughly one hour. Monitor install progress at http://localhost:8006.
cd LitterBox/Docker
chmod +x setup.sh
./setup.sh
# Monitor: http://localhost:8006
# RDP: localhost:3389
# LitterBox UI: http://127.0.0.1:1337Configure EDR integration (optional)
To dispatch payloads to a real EDR-instrumented VM and receive detection alerts, drop one or more EDR profile YAML files under Config/edr_profiles/. Follow the Elastic Defend or Fibratus setup guides in the repository wiki.
Add LitterBoxMCP to your MCP client
Configure your MCP client to connect to the LitterBoxMCP server so an AI agent can drive analysis end to end. The MCP server connects to your running LitterBox instance via its HTTP API.
Litterbox Examples
Client configuration
Configure Claude Desktop to connect to LitterBoxMCP. The server communicates with a locally running LitterBox instance.
{
"mcpServers": {
"litterbox": {
"command": "npx",
"args": ["litterbox"],
"env": {
"LITTERBOX_URL": "http://127.0.0.1:1337",
"LITTERBOX_API_KEY": "your-api-key-here"
}
}
}
}Prompts to try
These prompts demonstrate how an LLM agent can drive LitterBox payload analysis via the MCP interface.
- "Upload payload.exe and run the full static analysis pipeline. Report the Detection Score and list triggering YARA rules."
- "Submit the sample to the EDR profile 'elastic-defend' and return the correlated alert list."
- "Compare the detection results for payload_v1.exe and payload_v2.exe and identify what changed."
- "Run PE-Sieve and Hollows-Hunter on the uploaded sample and summarize any anomalies found."
- "What indicators caused the highest score increase in the last scan? Suggest evasion approaches to test."Troubleshooting Litterbox
LitterBox UI at http://127.0.0.1:1337 is unreachable after starting
On Windows, ensure you are running from an administrator shell. On Linux/Docker, wait for the full KVM Windows VM to boot and LitterBox to initialize inside it — this can take 10-20 minutes on first run. Check http://localhost:8006 for install progress.
YARA scanner returns no results or crashes
YARA rules are stored under Scanners/Yara/rules/. Verify that the elastic-yara and YARAForge rule directories exist and are populated. The yara64.exe binary must be present in Scanners/Yara/. Re-clone the repository if scanner binaries are missing.
EDR profile dispatch fails or returns no alerts
Confirm the EDR profile YAML in Config/edr_profiles/ has the correct IP, port, and credentials for the instrumented Windows VM. Verify the Whiskers agent is installed and running on the VM as described in the wiki's Whiskers Agent guide.
Frequently Asked Questions about Litterbox
What is Litterbox?
Litterbox is a Model Context Protocol (MCP) server that self-hosted sandbox for red teams to test payloads against modern detection before deployment. mcp integration lets an llm agent drive analysis end to end. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Litterbox?
Follow the installation instructions on the Litterbox GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Litterbox?
Litterbox works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Litterbox free to use?
Yes, Litterbox is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
Litterbox Alternatives — Similar Security Servers
Looking for alternatives to Litterbox? 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 Litterbox 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 Litterbox?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.