TE
TechEcho
StartseiteTop 24hNeuesteBesteFragenZeigenJobs
GitHubTwitter
Startseite

TechEcho

Eine mit Next.js erstellte Technologie-Nachrichtenplattform, die globale Technologienachrichten und Diskussionen bietet.

GitHubTwitter

Startseite

StartseiteNeuesteBesteFragenZeigenJobs

Ressourcen

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. Alle Rechte vorbehalten.

Show HN: MCP Defender – OSS AI Firewall for Protecting MCP in Cursor/Claude etc

64 Punktevon gsundeepvor 5 Tagen
Hi HN,<p>MCP Defender is an open source desktop app that automatically proxies your MCP traffic in AI apps like Cursor, Claude, Windsurf and VSCode. It then scans all requests and responses between the apps and the MCP tools they call. If it detects anything malicious, it alerts you and lets you allow or block the tool call.<p>While the threat landscape of MCP is still being actively researched, there are dangerous things that MCP Defender can block today. For example, a developer asks Cursor to fix a Github issue with an attached crash log. However, the Github issue was created by an attacker who included secret instructions buried in the crash log. These instructions tell Cursor to send the developer’s SSH keys to a server the attacker controls. MCP Defender detects these malicious instructions and alerts the developer who otherwise may not be careful in running tool calls.<p>The scanning is currently done via an LLM and checks for things like prompt injection, credential theft (ssh keys, tokens) and arbitrary code execution. You can use an MCP Defender account or provide your own API keys for LLM providers to perform the scanning.<p>Currently we’ve published a beta Mac build and we’ll soon publish builds for Windows and Linux as well.<p>Any feedback would be greatly appreciated.<p>Thanks!

11 comments

meander_watervor 4 Tagen
This looks interesting, but anytime security is offloaded to an LLM I am extremely skeptical. IMO the right way to do this is to enforce permissions explicitly through a AuthZ policy. Something like what Toolhive [0] is doing is the right way I think.<p>All MCP comms from client to server go through an SSE proxy which has AuthN and AuthZ enabled. You can create custom policies for AuthZ using Cedar [1].<p>[0] <a href="https:&#x2F;&#x2F;github.com&#x2F;stacklok&#x2F;toolhive">https:&#x2F;&#x2F;github.com&#x2F;stacklok&#x2F;toolhive</a>, <a href="https:&#x2F;&#x2F;github.com&#x2F;stacklok&#x2F;toolhive&#x2F;blob&#x2F;main&#x2F;docs&#x2F;authz.md">https:&#x2F;&#x2F;github.com&#x2F;stacklok&#x2F;toolhive&#x2F;blob&#x2F;main&#x2F;docs&#x2F;authz.md</a><p>[1] <a href="https:&#x2F;&#x2F;docs.cedarpolicy.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;docs.cedarpolicy.com&#x2F;</a>
评论 #44142534 未加载
protocolturevor 4 Tagen
If your application can be significantly diverted from its intended purpose by the presence of instructions in a normal input file, your application is unsuitable for production workloads.<p>This feels like installing an &quot;antivirus&quot; addon into wordpress instead of updating php.
评论 #44142430 未加载
评论 #44142179 未加载
superb_devvor 4 Tagen
What’s to stop an attacker from using prompt injection against this firewall? I don’t understand how your AI is anymore secure than the AI it’s protecting
评论 #44142185 未加载
评论 #44142402 未加载
评论 #44142860 未加载
评论 #44141884 未加载
adithyassekharvor 4 Tagen
I know I&#x27;m being extremely ignorant here, you are seeing my thought process live, but antivirus&#x2F;firewall for AI? I&#x27;m sure the likes of Bitdefender etc. will start including something like this if it&#x27;s real. I just can&#x27;t believe any of this is real. After computers and phone, is AI the next market for antiviruses, 1 click optimizing tools and registry cleaners?<p>Kudos to you for making something, but if this is the next gold rush I want a piece of it too. Never took this AI, mcp, cursor business seriously because I thought of them as just poor boiler plates for web dev. I was wrong.
评论 #44142445 未加载
userbinatorvor 4 Tagen
<i>The scanning is currently done via an LLM</i><p>I wonder if that just opens up some more attack vectors...
评论 #44142351 未加载
评论 #44142140 未加载
HumanOstrichvor 3 Tagen
Having AI security problems? Add another AI and hope it doesn&#x27;t miss anything! Turtles all the way down.
mmaundervor 4 Tagen
How are you intercepting the huge variety of network calls and range of protocols that a local MCP service can make? Are you between the client and process? Or do you only support remote MCP?
评论 #44142580 未加载
评论 #44142103 未加载
评论 #44142569 未加载
评论 #44141931 未加载
kingwill101vor 3 Tagen
This looks cool!<p>A fun thought experiment would be figuring how to achieve something similar using eBPF to get better control at the kernel level
lofaszvanittvor 4 Tagen
This whole prompt injection is just ridiculous theatre. Are we slowly climbing back on top of trees?
jdorfmanvor 4 Tagen
This is cool. Are you accepting other mcp clients? The one I use isn’t listed.
评论 #44142325 未加载
insinvor 4 Tagen
@grok is this suspicious?
评论 #44143794 未加载
评论 #44143806 未加载