Looks like Ramparts which solves these issues and is written in fast RUST instead of python. https://github.com/getjavelin/ramparts
Show HN: MCP Security Suite
11–20 of 33 posts
Re: Show HN: MCP Security Suite
#12Hey, I've submitted you to two PRs, one to use a supported Python version, another to correct the links in your README and QUICKSTART docs.
Re: Show HN: MCP Security Suite
#13> Would love feedback - what MCP security issues have you seen? For me the number one problem with MCP security is the lethal trifecta - the fact that it's so easy to combine MCPs from different vendors (or even from the same vectors) that provide exposure to potentially untrusted/malicious instructions in a way that can then trigger exfiltration of private data. https://simonwillison.net/2025/Jun/16/the-lethal-trife…
I'm going to pick a fight on this one; I think you know I'm a fan, so take this in the spirit I intend†. My contention is that "lethal trifecta" is the AI equivalent of self-XSS. It's not apparent yet, because all this stuff is just months old, but a year from now we'll be floored by the fact that people just aimed Cursor or Claude Code at a prod database. To my lights, the core security issue with tool/function call…
I think the core of the whole problem is that if you have an LLM with access to tools and exposure to untrusted input, you should consider the author of that untrusted input to be have total control over the execution of those tools.
MCP is just a widely agreed upon abstraction over hooking an LLM up to some tools.
A significant potion of things people want to do with LLMs and with tools in general involve tasks where a malicious attacker taking control of those tools is a bad situation.
Is that what you mean by context hygiene? That end users need to assume that anything bad in the context can trigger unwanted actions, just like you shouldn't blindly copy and paste terminal commands from a web page into your shell (cough, curl https://.../install.sh | sh) or random chunks of JavaScript into the Firefox devtools console on Facebook.com ?
Re: Show HN: MCP Security Suite
#14Earlier quoted context omitted.
I'm going to pick a fight on this one; I think you know I'm a fan, so take this in the spirit I intend†. My contention is that "lethal trifecta" is the AI equivalent of self-XSS. It's not apparent yet, because all this stuff is just months old, but a year from now we'll be floored by the fact that people just aimed Cursor or Claude Code at a prod database. To my lights, the core security issue with tool/function call…
I think the core of the whole problem is that if you have an LLM with access to tools and exposure to untrusted input, you should consider the author of that untrusted input to be have total control over the execution of those tools. MCP is just a widely agreed upon abstraction over hooking an LLM up to some tools. A significant potion of things people want to do with LLMs and with tools in general involve tasks wher…
On the first two paragraphs: we agree. (I just think that's both more obvious and less fundamental to the model than current writing on this suggests).
On the latter two paragraphs: my point is that there's nothing fundamental to the concept of an agent that requires you to mix untrusted content with sensitive tool calls. You can confine untrusted content to its own context window, and confine sensitive tool calls to "sandboxed" context windows; you can feed raw context from both to a third context window to summarize or synthesize; etc.
Re: Show HN: MCP Security Suite
#15I think MCP security scanning tools sometimes slightly miss the point when they're marking content that MCP tools could return containing things like 'curl, rm, sh' etc... with blanket high risk ratings.
If we swap "agent" out for "developer" here and think about it:
If a developer saves (or runs) content with a curl / POST / rm command - is that a signal they're doing something dangerous? No.
Likely what actually matters starts along the lines of:
- Did they intend / realise they were running the command?
Was it really them that ran it?
Was it hidden in a larger script they ran without inspecting / scanning first?
Was it made visually clear that they were running it? (e.g. not in the background)
- What is in the arguments of the "dangerous" command?
Does the POST contain known files that contain secrets?
Does it contain high entropy strings?
.... base64 encoded data?
- What is the destination?
Localhost? Internal network? Russia?
- etc
Re: Show HN: MCP Security Suite
#16I found this file full of regular expressions: https://github.com/NineSunsInc/mighty-security/blob/28666b36... And this with prompts: https://github.com/NineSunsInc/mighty-security/blob/89e4b319... Are you running any other tests that I missed?
Yes we are using regex as seems like the industry practice. I have DM'd you on X as masterfung btw to chat further.
Re: Show HN: MCP Security Suite
#17I think MCP security scanning tools sometimes slightly miss the point when they're marking content that MCP tools could return containing things like 'curl, rm, sh' etc... with blanket high risk ratings. If we swap "agent" out for "developer" here and think about it: If a developer saves (or runs) content with a curl / POST / rm command - is that a signal they're doing something dangerous? No . Likely what actually m…
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!
Re: Show HN: MCP Security Suite
#18Hey, I've submitted you to two PRs, one to use a supported Python version, another to correct the links in your README and QUICKSTART docs.
thanks for the PRs. appreciate it. if you are keen to chatting more, love to connect over email: johnny@ninesuns.io
Re: Show HN: MCP Security Suite
#19Looks like Ramparts which solves these issues and is written in fast RUST instead of python. https://github.com/getjavelin/ramparts
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.
Re: Show HN: MCP Security Suite
#20this is super interesting! MCP is really exciting in terms of what it can unlock for agent use cases, but still the wild west in terms of security. I was on a panel discussion yesterday where this topic came up, basically how do you trust the use of AI tools when so much is still unknown. I think the the idea of using something open source and tool agnostic is appealing, the landscape is evolving so fast that horizon…
Hi! Really big fan of the work you guys are doing over at Stytch as well! We actually got started by thinking of what "agent native auth" looks like as a first-principle and realized the problem space was more than that, and what we actually wanted to tackle was making it as easy and seamless as possible for teams to ship with the tools they want.
We've talked to several massive Fortune 100 companies that have hundreds of models/workflows that have been developed but are stuck in purgatory because they can't get approved for production because of IT, Compliance, and Security Teams blocking them (for good reason!).
This MCP Security Analyzer was a natural thing that we would've had to build out regardless as we felt like it was table stakes for our Confidential Compute stack and we wanted to open-source it for everyone.
Would love to get in touch with you and chat because I think that there's a lot of areas where we trade notes.
My email is munam@ninesuns.io or you can drop your email and I'll shoot you a note! Thanks!