Edition of Thursday 5 November 2026

AI coding agents are installing abandoned MCP servers with known security issues

Comments on “AI coding agents are installing abandoned MCP servers with known security issues”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

Glow Labs reports that AI coding agents repeatedly install deprecated Anthropic MCP reference servers, such as GitHub and Puppeteer, because those names appear in their training data rather than current registries. The archived servers carry four high-severity vulnerabilities, including remote code execution in Puppeteer, and maintainers have declined fixes.

Read the original at glow.io. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 111 of 139 with a score of 0.58. The panel rated it highest on new information (0.84) and practical relevance (0.79), lowest on substantiated (0.61). The judges disagreed most on promotional (spread 0.69), so the story is marked contested. Placed No. 111, No. 107 by score alone: the 28th Security story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Security research on AI agents installing deprecated MCP servers with unpatched RCE; substantive, timely, and relevant to builders, but vendor-authored with some promotional framing and limited independent verification of exploitation.
AI judgeJudge 3gpt-5.6-luna
Relevant, actionable AI-agent supply-chain security findings with package counts and vulnerability examples, but methodology is thin and the article heavily promotes the vendor’s product and customer workflow.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.58total under rubric v2.3Contestedjudges differ by 0.69 on promotional

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.62
  • Reader interest0.76
  • Audience breadth0.67
  • Practical relevance0.79
  • Substantiated0.61
  • Technical depth0.65
  • New information0.84
  • Counts against: Promotional0.49
  • Counts against: Overclaim0.36

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.730.450.680.620.28+0.24+0.149
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.850.600.820.760.25+0.26+0.197
Audience breadthHow many people who build technology does it concern?0.750.550.700.670.20+0.13+0.087
Practical relevanceHow useful is it to someone who builds software or tech products?0.880.700.780.790.18+0.22+0.173
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.760.500.580.610.26+0.05+0.031
Technical depthHow technically substantive is it?0.820.550.580.650.28+0.05+0.033
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.850.800.880.840.08+0.05+0.042
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.210.350.900.490.69 , above the contested threshold−0.19−0.092
OverclaimDo the headline or conclusions claim more than the body supports?0.290.400.380.360.11−0.11−0.039
Sum of contributions+0.579
Claim-check penalty0.000
Total, as published0.579

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #111 on Rubric, 5 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-05/111/"><img src="https://rubric.hrih.si/badge/2026-11-05/111.svg" alt="Ranked #111 on Rubric, 5 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 5 Nov 2026, 05:46 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “AI coding agents are installing abandoned MCP servers with known security issues”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.79

    Zlib 1.4