PulseAugur
EN
LIVE 08:48:57

AI agent tools face security risks as new scoring systems emerge

By PulseAugur Editorial · [2 sources] ·

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

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.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI agent tools face security risks as new scoring systems emerge

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Two companies released new platforms for scoring the security and reliability of AI agent tools, addressing a growing supply chain risk.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
106 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. dev.to — MCP tag TIER_1 English(EN) · Om Shree ·

    Manifold Security Just Scored 7,700 MCP Servers. Here's Why That Number Should Worry You.

    <p>The MCP ecosystem grew faster than anyone could audit it. Now there's a tool trying to catch up — and what it's finding isn't reassuring.</p> <h2> The Problem It's Solving </h2> <p>When <a href="https://modelcontextprotocol.io/" rel="noopener noreferrer">Model Context Protocol…

  2. dev.to — MCP tag TIER_1 English(EN) · Dinesh Kumar ·

    We Scored 14,800+ MCP Servers on Behavioral Trust. Here's What We Found.

    <h2> The MCP ecosystem has a trust problem — and scanning source code won't fix it </h2> <p>The Model Context Protocol ecosystem is growing fast. Thousands of MCP servers now offer tools that AI agents call autonomously — executing code, querying databases, moving money, managing…

RELATED ENTITIES

RELATED TOPICS