Flagged: privileged Docker. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by deonmenezes · MCP Server · ★ 503
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mantishack safe to install? View the security audit →
Mantishack Ethically hack and discover vulnerabilities in any software with the power of AI. mantishack.com · Upstream: github.com/gadievron/raptor Built on top of RAPTOR Mantishack is a fork of RAPTOR — the Recursive Autonomous Penetration Testing and Observation Robot by Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake), Michael Bargury, and John Cartwright. The agentic workflow, the Semgrep + CodeQL pipeline, the multi-stage validation methodology, the persona library, and the offline registry packs all come from RAPTOR. Mantishack carries that work forward, rebrands the user-facing surface to the slash-command vocabulary, adds an automatic auth + logging audit lane (JWT, cookies, audit-log coverage), and ships under MIT with two coexisting copyrights. Upstream licence: MIT © 2025-2026 Gadi Evron, Daniel Cuthbert, Thomas Dullien (Halvar Flake), Michael Bargury, John Cartwright — see . Fork-modification licence: MIT © 2026 Deon Menezes — see . Combined attribution and modification log in . If you came here looking for the canonical project, please visit [github.com/gadiev
| Stars | 503 |
| Forks | 74 |
| Language | Rust |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 62.8782839325207/100 |
| Open Issues | 109 |
| Last Updated | 2026-10-03 |
| Created | 2026-04-05 |
| Platforms | claude-code, mcp, rust |
| Est. Tokens | ~26k |
These tools work well together with mantishack for enhanced workflows:
Looking for a mantishack alternative? If you're comparing mantishack with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a
An agent-native web security workspace. Find vulnerabilities through red-teaming. Formally verify properties o
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Explore other popular mcp server tools:
mantishack is Mantis Hack. It is categorized as a MCP Server with 503 GitHub stars.
mantishack is primarily written in Rust. It covers topics such as agent-harness, ai-agents, autonomous-agents.
You can find installation instructions and usage details in the mantishack GitHub repository at github.com/deonmenezes/mantishack. The project has 503 stars and 74 forks, indicating an active community.
mantishack is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to mantishack on Agent Skills Hub include pentest-ai-agents, CyberStrike, pentest-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: