jodoking
jodoking on Hacker News
super excited to share this with the community. and looking forward to your feedback. i am part of the team behind this tool.
sorry for the issues you are facing. can you let me know what was the issue? the repo can scan github mcp server code posted in the repo like
https://github.com/punkpeye/awesome-mcp-servers and provide a quick, deep, or deep with ai analysis. let us know if there is anything we can help with.
great question. the way we are thinking about it is keeping a list of endpoints that can aid in getting the latest vulnerabilities, keywords, and patterns to detect. we don't know when that is released but that is on our roadmap for sure.
thanks for sharing this. did not know about them. from initial glances, there are a few things we are aiming to do on our roadmap that they have already working (inspiration). however, our goal is to add audits, database of scans, ability to contribute scans to a service that dev can look and avoid, and more.
thanks for the PRs. appreciate it. if you are keen to chatting more, love to connect over email:
[email protected]
you brought some great points. what we are hoping to do next iteration is to add audit logs of actions taken (of high risk actions) that way even if the user "accidentally" blank agrees their mcp service to take the rm action then at least they can see if the action was something they typed or suggested by the LLM.
if you have some improvements around this space love to chat and collaborate!
Yes we are using regex as seems like the industry practice. I have DM'd you on X as masterfung btw to chat further.
I know right? I mean the timing is great. I love MCP but cant stand how unsafe it is. I think there are greatness ahead if we are able to fix this security issue. This was made around the idea to be as seamless as possible, as we built a dashboard, drop in a GH project MCP server link, and have a local DB to show what you ran. We have more great things ahead. But give it a try and let us know what you think!
Appreciate the interest and the first comments man. We like how fast Cerebras is and its importance to making the scanning fast! Yeah we have thought about this being part of dev workflow via Github Actions and locally for the dev environment too. Love to hear what you are building!
Posted by
jodoking on Thursday August 14, 2025 @04:01PM
from the show-hn dept.
https://github.com/NineSunsInc/mighty-security
Hi HN!We kept seeing devs get pwned through MCP tools in ways that security scanners completely miss. So we built an open-source analyzer to catch these attacks. Our first OSS by Mighty team.The problem: At Defcon, we saw MCP exploits with 100% success rate against Claude and Llama. Three attack patterns:Hidden Unicode in "error messages" - Paste a colleague's error into Claude, your SSH keys...
Posted by
jodoking on Wednesday June 25, 2025 @10:06AM
from the show-hn dept.
https://www.mightynetwork.ai/
Hey HN — I’m Johnny, co-founder of Mighty (https://mightynetwork.ai).The problem
AI agents can think, but the moment they need your data they hit a wall — security teams won’t let PII, payroll, or customer records leak out. OAuth exists for humans, not code running on its own.Our take (super-hero style)
• Headquarters — an end-to-end–encrypted data vault (client-side 256-bit) where you park...
We are developing an agent authentication and policy engine for the modern era. Traditional human authentication via Rails is not scalable, and the agent authentication system that requires users to input passwords is not scalable either. We are working on a solution that improves this significantly without compromising security, compliance, ownership, or speed. We envision a future where agents interact directly with each other, and the current authentication and policy systems need to evolve to handle private data use cases while meeting compliance, security, control, and interoperability requirements. Our goal is to enable resource owners (entities with private data or sensitive materials) to set agentic policies for external parties who meet the necessary requirements to access the data without the need for a user interface or user experience. We combine agentic-ready authentication, policy, and encryption. We welcome your thoughts if you would like to test it out. Our target audience is the enterprise space.
Posted by
jodoking on Saturday May 17, 2025 @08:12PM
from the mightynetwork.ai dept.
Posted by
jodoking on Monday September 25, 2023 @02:06PM
from the self-post dept.
Hi guys. I am a software engineer working on an open source protocol to enable ai to ai communication. If you are interested in this space, is technical, and have domain expertise, I would love to connect with you.Thanks for your time!Johnny
I don't use Yahoo. Are there other ways to sign up without having to sign up for another email address?