What did Hlido score MCP Queen?

MCP Queen scored 76/100 (STEADY) in Hlido's independent, hands-on review.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

MCP Queen

Name: MCP Queen review
Item: MCP Queen
Rating: 76
Author: Hlido Editor

Frameworks & Eval · tested 2026-08-05 · re-test due 2026-11-05 · by the Hlido desk, not the vendor

In short: An MCP discovery and evidence layer with real corpus scale and — rarest of all in this category — an explicit statement of what its grades do NOT mean.

4 PASS · 1 FAIL of 5 public-surface claims

Visit MCP Queen → scorecard.json

Quick answer

MCP Queen scores 76/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-05). STEADY (76) for corpus scale (18,849 indexed / 9,326 graded), a published ecosystem report with a falsifiable headline finding, and unusually disciplined scoping — it states outright that an operational grade is not a se Pricing was not findable on the public surface when tested.

Hlido Editor · 2026-08-05

MCP Queen indexes the MCP server ecosystem and attaches dated operational evidence to what it finds: 18,849 servers indexed, 9,326 graded live, plus separate Trust Receipts, field reports, and a published State of the MCP Ecosystem report whose lead finding (1 in 6 remote servers is dead) is the kind of unflattering number that suggests the measurement is real rather than promotional. The scoping discipline is what stands out. The site states plainly that "an operational grade is not a security certification", separates discovery from evidence from receipts rather than collapsing them into one number, and frames itself as "an experiment by Health AI" instead of overclaiming institutional authority. That is the correct posture for a rating layer, and we say so as a party with an obvious interest in the same discipline. What is missing is the layer beneath the claim: the grading methodology is not visible on the surface we captured, so a reader cannot yet tell what a grade measures or how it could be gamed; there is no independent validation of the index; and the self-description as an experiment leaves continuity genuinely uncertain for anyone who would depend on it. STEADY on scope, honesty and corpus size — with the caveat that a grading system is only as good as the method it will not show you.

Why STEADY

STEADY (76) for corpus scale (18,849 indexed / 9,326 graded), a published ecosystem report with a falsifiable headline finding, and unusually disciplined scoping — it states outright that an operational grade is not a security certification and keeps discovery, evidence and receipts as separate layers. Held below VITAL because the grading methodology is not exposed on the public surface, there is no third-party validation of the index, and the project describes itself as an experiment, which makes continuity uncertain.

Public-surface checklist

PASS Homepage loads (required)
PASS Primary value prop (required) — 'Find MCP Servers. Inspect the Evidence.'
PASS Cta present (required) — 'Search an MCP'
FAIL Pricing or access — No pricing or access terms on the captured surface
PASS Evidence or demo — Live counts, an example trust report, field reports, and a published ecosystem report

What we saw

4 screenshots captured by the Hlido engine during the reviewed run (run-2a9d41c14257734e-mcpqueen-com). Our own captures — not vendor marketing material.

MCP Queen — run screenshot 1 (home.png) — home.png

MCP Queen — run screenshot 2 (page_registry.png) — page_registry.png

MCP Queen — run screenshot 3 (page_mcp-security-evidence.png) — page_mcp-security-evidence.png

MCP Queen — run screenshot 4 (page_field-reports.png) — page_field-reports.png

What it does well

Real corpus scale — 18,849 servers indexed, 9,326 graded live
States explicitly that an operational grade is not a security certification, rather than letting readers over-read it
Keeps discovery, dated operational evidence and Trust Receipts as separate layers instead of one composite number
Publishes an ecosystem report with an unflattering, falsifiable headline (1 in 6 remote servers is dead)
Use-case comparison entry points (databases, web search, health research, finance, dev tools) suit real buyer questions
An explicit 'For Agents' surface — the index is meant to be machine-consumed

What it fails at

Grading methodology is not visible on the public surface — a reader cannot tell what a grade measures or how it might be gamed
No third-party validation of the index or the grades
Self-described as 'an experiment by Health AI', which leaves continuity uncertain for anyone depending on it
Evidence freshness and re-grading cadence are not stated on the surface we captured
The playful court/queen framing sits awkwardly against the seriousness of grading other people's infrastructure

Best for

Teams choosing among MCP servers who want operational evidence rather than a README's self-description
Agent builders who need a machine-readable index of what MCP servers exist and which are alive
Anyone auditing MCP ecosystem health at population scale

Not recommended for

Buyers who need a security certification — the site correctly says this is not one
Procurement processes that require a published, auditable grading methodology
Anyone needing a contractual guarantee of continuity from a self-declared experiment

Pricing & access

Pricing findable on the public surfaceFAIL No pricing or access terms on the captured surface (tested 2026-08-04)

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-04.

Compared to

Glama AI Glama

Agent relevance

API MCP Behavioral-testable

Agentic-Commerce Readiness 71/100 · INTEGRABLE

Independent readiness for agent delegation & transaction. How it’s scored · check live

Ships an API and a dedicated 'For Agents' surface, and the whole product is an index built to be queried programmatically. An agent choosing which MCP server to connect to is the explicit primary consumer.

Agent-friendly score: 8/10

Evidence

18,849 MCP servers indexed, 9,326 graded live — source (2026-08-05) verified
An operational grade is explicitly not a security certification — source (2026-08-05) verified
State of the MCP Ecosystem (July 2026): 1 in 6 remote servers is dead — source (2026-08-05) verified
Separate Trust Receipts and dated field reports alongside the registry — source (2026-08-05) verified
Grading methodology and re-grading cadence — source (2026-08-05)

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface-tier-1+editorial-narrative-v2 · Methodology version 2026.05 · Next review due 2026-11-05

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/mcpqueen-mcpqueen.svg)](https://hlido.eu/check/?agent=mcpqueen-mcpqueen)

HTML

<a href="https://hlido.eu/check/?agent=mcpqueen-mcpqueen"><img src="https://hlido.eu/badge/mcpqueen-mcpqueen.svg" alt="Hlido trust score"></a>