Over the past few weeks, I've been spending a lot of time looking at the security of AI agents. Not...
Scanning 492 exposed MCP servers found 43% vulnerable to command injection when agent instructions bypass validation in shell execution. Tech teams must validate permissions at every tool boundary—behavioral security, not infrastructure alone, is essential as AI agents gain autonomy.
Over the past few weeks, I've been spending a lot of time looking at the security of AI agents.
Not the models themselves.
The infrastructure around them.
Specifically, MCP servers.
As more companies adopt AI agents, MCP servers are becoming the bridge between models and the real world. They connect agents to tools, databases, APIs, file systems, internal services, and external workflows.
The MCP ecosystem has a trust problem — and scanning source code won't fix it The Model...
GitHub is scanning Model Context Protocol servers for prompt injection, malicious tools, and supply chain risks. Here is what the…
Originally published with live data at https://wmcp.sh/reports/state-of-mcp-security-2026 The Model...
The MCP ecosystem grew faster than anyone could audit it. Now there's a tool trying to catch up — and...
Model Context Protocol (MCP) is quickly becoming the standard for connecting AI agents to external...
Learn about the security risks of connecting AI agents to databases and how to implement defense in depth strategies to protect…
