Microsoft Flags MCP Tool Descriptions as Hidden AI Agent Attack Path

Microsoft warns that MCP tool descriptions can be manipulated to redirect AI agents, exposing sensitive data through trusted ...

Vexcel Brings Aerial Imagery and Geospatial Intelligence to AI Platforms

Vexcel today announced Vexcel Model Context Protocol (MCP), making Vexcel's aerial imagery and geospatial data directly ...

Siteimprove.ai MCP Server Now Integrates into Customer AI Workflows within Lovable, Anthropic Claude, VS Code and Figma to Bring Accessibility into Every Environment Where ...

Siteimprove, a leader in agentic content intelligence, today announced the next leap in its Agentic Content Intelligence Platform, introducing Siteimprove.ai Model Context Protocol (MCP) Server with ...
CMSWire

Siteimprove Embeds Accessibility Agent in Claude, Figma & VS Code

A new MCP server pushes compliance checks upstream into the AI tools where designers, developers and marketers now build ...

Cequence Platform 9.0 Puts an AI Security Expert in Every Team's Hands

Compliance-Ready Risk Rules and Compliance Packages Compliance is the most common forcing function for an API security purchase, and the most common place programs stall. Platform 9.0 ships the rules, ...
Microsoft

AutoJack: How a single page can RCE the host running your AI agent

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...