AI agent tools for pentesting
Short answer: Our top pick for pentesting: osmedeus, with the highest AgentPick Score (72/100) among tools tagged "pentesting". Runners-up: burp-ai-agent (70) and jadx-ai-mcp (54). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | osmedeus | A Modern Orchestration Engine for Security | 72/100 | ★ 6.6k | MIT | 4 Oct 2026 |
| #2 | burp-ai-agent | Burp Suite extension that adds built-in MCP tooling, AI-assisted analysis, privacy controls, passive and active scanning and more | 70/100 | ★ 1.5k | MIT | 14 Oct 2026 |
| #3 | jadx-ai-mcp | Plugin for JADX to integrate MCP server | 54/100 | ★ 2.9k | Apache-2.0 | 23 Sept 2026 |
| #4 | AgentHound | Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across M… | 53/100 | ★ 450 | Apache-2.0 | 14 Oct 2026 |
| #5 | BurpMCP-Ultra | AI-powered MCP server for Burp Suite Professional — 149 tools across proxy, scanner, inline fuzzer, race conditions, guided injection, JWT/IDOR attack… | 53/100 | ★ 272 | MIT | 28 Sept 2026 |
| #6 | ai-security-tool | 🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI age… | 52/100 | ★ 622 | MIT | 13 Oct 2026 |
| #7 | evil-winrm-py | Execute commands interactively on remote Windows machines using the WinRM protocol (just faster) | 48/100 | ★ 412 | MIT | 11 Oct 2026 |
| #8 | Cairn | Cairn is a general-purpose AI state-space search engine, validated first on autonomous penetration testing. Sometimes misspelled as Carin. | 44/100 | ★ 3.6k | AGPL-3.0 | 7 Sept 2026 |
| #9 | h1-brain | MCP server that connects AI assistants to HackerOne for bug bounty hunting | 34/100 | ★ 358 | MIT | 13 Oct 2026 |
| #10 | agentseal | Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resist… | 27/100 | ★ 377 | See repo | 11 Jun 2026 |
| #11 | MCP-Kali-Server | MCP configuration to connect AI agent to a Linux machine. | 22/100 | ★ 847 | MIT | 17 Mar 2026 |
| #12 | pentest-agents | Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP serve… | 21/100 | ★ 1k | See repo | 12 Jun 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.