Back to browse
Hackerdogs Preview 2 Released

Hackerdogs Preview 2 Released

by tredkar·Mar 12, 2026·1 point·0 comments

AI Analysis

MidBold Bet

Enterprise security with 150+ MCP servers, but login-only landing page shows nothing.

Strengths
  • Scheduled continuous discovery instead of one-time scans
  • MCP server integration enables extensible agent workflows
Weaknesses
  • Landing page is just login — no demo, pricing, or feature details visible
  • Enterprise security crowded with Wiz, Lacework, SecurityScorecard
Category
Target Audience

Security teams and DevOps leads

Similar To

Wiz · Lacework · SecurityScorecard

Post Description

Team, I started Hackerdogs back in Oct 2025 with the vision of delivering the right intelligence, at the right time, to the right people. When I was running larger Dev and Sec teams, I struggled to get real-time information on the company's overall security posture and its apps. I had to face customers during incidents with little to no data. Hackerdogs was born to solve this problem in an AI-native way so that people don't have to run around to get real-time threat and posture data. With the success of Preview 1 (announced Feb 2nd), we made massive progress with Preview 2. Preview 1 was a Chat experience with 150+ MCP servers integrated and multi-agent workflow. The theme of Preview 2 is: One-Click Attack Surface Discovery: See your Organization the Way Hackers Do. New features: 1) Scheduled prompts discover your attack surface and other posture information continuously 2) One-click Attack Surface Discovery 3) APIs and Hackerdogs MCP Server so you can use Hackerdogs in Claude or in your own pipeline 4) 200+ Security and OSINT MCP Servers integrated 5) Webhooks to Slack, Teams, Discord and Custom APIs Would love feedback. Contributors welcome. Try it: https://preview.hackerdogs.ai Thanks, Tej Founder, CEO https://hackerdogs.ai

Similar Projects

SecurityPass

Synesthetic Computation

The author walks the reader through a full exploit chain that starts with a UX/trust-boundary trick and ends in RCE by causing a client to connect to an attacker gateway, leak a token, and reconfigure the agent’s execution environment. It's a sharp systems narrative that will change how you think about agents crossing chat, browser, and local tooling — excellent reading for defenders and attacker-minded engineers, but it's an investigative article rather than a ship-or-tool.

WizardryRabbit Hole
agamrafaeli
103mo ago