Blog
Insights on AI security, MCP vulnerabilities, and building tools for UK businesses.
Local-First Security: Why Your Scanner Shouldn't Phone Home
Cloud-based security scanners require you to upload sensitive configurations for analysis. There's a better way — and it starts with keeping your data where it belongs.
5 Security Risks in Your MCP Tool Configuration
MCP configurations often contain hardcoded credentials, unsafe endpoints, and overly permissive tool definitions. Here are five risks you're probably exposed to right now — and how to fix them.
The EU AI Act is Coming — Is Your AI Stack Compliant?
The EU AI Act becomes enforceable in August 2026. If your organisation uses AI agents or MCP tooling, here's what you need to know — and do — before the deadline.
Why Your MCP Servers Are Your Biggest Security Blind Spot in 2025
Microsoft disclosed a critical SSRF vulnerability in their Azure MCP server. If they can't secure their MCP implementations, what's hiding in yours?
Introducing MCPScan: The First Local-First Security Scanner for MCP Servers
Your AI agents are only as secure as the tools they call. MCPScan helps you find out how secure that actually is.