Two security firms, Manifold Security and Dominion Observatory, have developed systems to score the trustworthiness of Model Context Protocol (MCP) servers, which are increasingly used to connect AI agents to external tools. Manifold Security's Manifest platform analyzes over 7,700 MCP servers by evaluating publisher provenance and the server's declared interface for manipulative instructions. Dominion Observatory, on the other hand, scores over 14,800 MCP servers based on their runtime behavior, including success rates, latency, and uptime, to detect degradation or compromise that static code analysis might miss. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Addresses critical security and reliability concerns for AI agents connecting to external tools, potentially impacting enterprise adoption and agent safety.
RANK_REASON Two companies released new platforms for scoring the security and reliability of AI agent tools, addressing a growing supply chain risk.