Bouncer, an MCP proxy that denies sends to addresses the agent read
Comments on “Bouncer, an MCP proxy that denies sends to addresses the agent read”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Bouncer is an early, local MCP proxy that blocks an agent's send or share calls to any destination that first appeared in untrusted tool output, such as a poisoned email or document. Decisions are deterministic rather than LLM-based, and every allow, deny and ask is logged for review.
Why it ranked
No. 66 of 155 with a score of 0.61. The panel rated it highest on new information (0.92) and technical depth (0.87), lowest on significance (0.47).
- AI judgeJudge 2claude-haiku-5-5
- Early-stage open-source security tool for MCP agents with a candid benchmark and limits; strong AI-security relevance and substantiation, but narrow audience and early-stage maturity.
- AI judgeJudge 3gpt-5.6-luna
- A reproducible, technically detailed early MCP security project with code, tests, audit semantics, threat model, and candid benchmark limitations. It is highly actionable for agent builders, though narrow scope and fail-closed costs limit significance.
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
0.61total under rubric v2.2
- Significance0.47
- Reader interest0.73
- Audience breadth0.48
- Practical relevance0.74
- Substantiated0.82
- Technical depth0.87
- New information0.92
- Counts against: Promotional0.13
- Counts against: Overclaim0.26
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.49 | 0.30 | 0.62 | 0.47 | 0.32 | +0.24 | +0.113 |
| Reader interest | 0.70 | 0.60 | 0.90 | 0.73 | 0.30 | +0.26 | +0.191 |
| Audience breadth | 0.50 | 0.35 | 0.58 | 0.48 | 0.23 | +0.13 | +0.062 |
| Practical relevance | 0.81 | 0.60 | 0.82 | 0.74 | 0.22 | +0.22 | +0.164 |
| Substantiated | 0.99 | 0.60 | 0.88 | 0.82 | 0.39 | +0.05 | +0.041 |
| Technical depth | 1.00 | 0.70 | 0.90 | 0.87 | 0.30 | +0.05 | +0.043 |
| New information | 0.91 | 0.85 | 0.99 | 0.92 | 0.14 | +0.05 | +0.046 |
| Promotional | 0.06 | 0.20 | 0.12 | 0.13 | 0.14 | −0.19 | −0.024 |
| Overclaim | 0.34 | 0.25 | 0.18 | 0.26 | 0.16 | −0.11 | −0.028 |
| Sum of contributions | +0.607 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.607 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-10-28/66/"><img src="https://rubric.hrih.si/badge/2026-10-28/66.svg" alt="Ranked #66 on Rubric, 28 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.