MCP ConfigsMay 12, 2026·2 min read

LitterBox — Self-Hosted Payload Sandbox (MCP)

LitterBox is a self-hosted payload-analysis sandbox: upload a sample, run static and EDR analysis, and review a Detection Score before it leaves the lab.

MCP Hub
MCP Hub · Community
Agent ready

Safe staging for this asset

This asset is staged first. The copied prompt tells the agent to inspect the staged files and ask before activating scripts, MCP config, or global config.

Stage only · 17/100Policy: stage
Agent surface
Any MCP/CLI agent
Kind
Mcp Config
Install
Stage only
Trust
Trust: Established
Entrypoint
Asset
Safe staging command
npx -y tokrepo@latest install 3a4c4478-0dd6-59d2-a592-8a83a8eddd05 --target codex

Stages files first; activation requires review of the staged README and plan.

Intro

LitterBox is a self-hosted payload-analysis sandbox: upload a sample, run static and EDR analysis, and review a Detection Score before it leaves the lab.

  • Best for: Red/blue teams who need a repeatable lab sandbox to measure detection before live engagements
  • Works with: Python 3.11+; Windows and Docker (Linux); optional EDR profiles; includes a wiki-linked MCP integration (per README)
  • Setup time: 30–90 minutes (Docker build can take ~1 hour)

Practical Notes

  • GitHub: 1,416 stars · 161 forks; pushed 2026-05-05 (verified via GitHub API).
  • README states Docker setup provisions a Windows 10 container with KVM and exposes UI at http://127.0.0.1:1337.
  • README lists bundled scanners with versions/dates (e.g., PE-Sieve 0.4.1.2 updated 2026-05-02; Elastic YARA rules commit d131ea8).

Main

If you use LitterBox in a real workflow, keep it disciplined:

  1. Treat it as a staging gate: every payload must pass the same pipeline before it leaves the lab.
  2. Keep EDR profiles and scanner versions under change control; the README’s scanner table makes drift visible.
  3. Use the results to decide between:
    • rewrite/refactor (reduce detections)
    • environmental changes (different execution context)
    • abandon (too risky)
  4. Run it isolated. The README’s advisory calls out VM isolation and “development use only”.

Even if you never use the MCP path, the “Detection Score + indicators breakdown” framing is a strong way to standardize review discussions.

FAQ

Q: Is this safe to run on a workstation? A: Only in isolated environments. The README warns against production use and recommends VM/dedicated lab setups.

Q: Where do EDR profiles live? A: README says to drop YAML profiles under Config/edr_profiles/ so the upload page picks them up at boot.

Q: Does it support MCP? A: README links to a wiki page named LitterBoxMCP under its documentation table.

🙏

Source & Thanks

Source: https://github.com/BlackSnufkin/LitterBox > License: GPL-3.0 > GitHub stars: 1,416 · forks: 161

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

Hister — Self-Hosted Search Engine (MCP-ready)

Hister is a privacy-focused self-hosted search engine that full-text indexes visited sites locally, with optional semantic search and MCP agent access.

MCP Configs
MCP Hub

MCP SSH Manager — Remote Ops via Claude/Codex

MCP SSH Manager is an MCP server that lets Claude Code and OpenAI Codex manage SSH sessions: run commands, sync files, and automate DevOps routines.

MCP Configs
MCP Hub

iai-mcp — Open-Source Memory System for AI Coding

iai-mcp is an open-source local memory layer for AI coding assistants. It runs an MCP server plus capture/recall hooks and ships benchmarks.

MCP Configs
MCP Hub

Google Workspace MCP — Gmail Drive Calendar for AI

Official Google CLI with built-in MCP server for all Workspace APIs. One command gives AI agents access to Gmail, Drive, Calendar, Docs, Sheets, and 10+ Google services.

MCP Configs
MCP Hub
◈Home🔍Search👤Me