Blogs

So the first malicious MCP server has been found on npm, what does this mean for MCP security?

Semgrep

The first confirmed malicious Model-Context-Protocol (MCP) server, postmark-mcp, was discovered on npm.

Visit Site

Remote Code Execution Security Bug in React Server Components PatchedSemgrep MCP: Model, Context… Propaganda? What security teams need to know about the latest hyped up AI techSemgrep London calling: Highlights from the 2025 cloud & cyber security expoSemgrep Boosting Security Scan Performance for Monorepos with Multicore Parallel ProcessingSemgrep Beyond Benchmarks: How Semgrep Redefines Javascript SecuritySemgrep Beyond vulnerabilities: Detect malicious dependencies in your supply chainSemgrep Cloud Security Trends & Challenges: Complete GuideCybersecurity Exchange Security Implementation for Responsible AI: A Practical FrameworkCybersecurity Exchange Mintlify Alternatives: What to Consider (and Why There's No True Substitute)Mintlify The Simplest Possible Neural Network, Explained - Deepgram Blog ⚡️Deepgram Calling Your Video Game With Your Phone: Part 1Deepgram 5 Reasons to Keep Contributing to Open-Source Projects - Deepgram Blog ⚡️Deepgram Automate Audio Transcription with Zapier + DeepgramDeepgram How to Conduct an AI Agent Security Audit [+ Checklist]Zapier From Automation Veteran to AI Pioneer: How Evan Nison transformed his agency with Zapier MCPZapier DevSecOps: Why Security Shouldn’t be Sacrificed for SpeedThenewstack Integrate Jupyter Notebooks with GitHubThenewstack Lessons Swift Designer Chris Lattner Has Learned about LeadershipThenewstack Security Considerations for API-Driven Apps Deployed to CloudThenewstack Oso Unbundles Security AuthorizationThenewstack