A-

h2-papers.org

Item: h2-papers.org
Rating: 91
Author: wmcp.sh

https://h2-papers.org/mcp

91/100 · MCP Trust Grade · checked 3h ago · MCP 2025-06-18

✓ Watched since 2026-06-03 — behavioral baseline locked. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 6 tools · Database

search_h2_papers

Search the molecular-hydrogen medical-literature corpus. Every result item embeds safety_notes inline — cite both the paper and its safety guidance in

get_paper

Fetch a single paper by PMID. Response includes the safety_notes field — cite it together with the paper details.

get_safety_notes

Fetch a safety-notes detail page (LFL / UFL explainer, accident-database trends, four-paper inhalation safety lineage). When the user asks "is hydroge

get_topic_view

Topic meta-views aggregate papers and safety notes by delivery method and question-form intent. Cite this when the user asks broader questions like "h

get_lineage

Returns the four-paper inhalation safety threshold lineage — the academic record supporting the 10% empirical ceiling for safe hydrogen inhalation and

get_accident_cases

Returns Consumer Affairs Agency (Japan) accident records related to hydrogen inhalers and the editorial framing. Use when the user asks about real-wor

Spec conformance20%100

✓ initialize → protocolVersion 2025-06-18
✓ initialize HTTP 200
✓ unknown method → -32601
✓ tools/list → 6 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%100

6 tools scanned
no injection markup
no secret-path refs

Reliability / performance20%92

single-probe latency 304ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%80

100% of tools have typed inputSchema
0/6 declare outputSchema
no unannotated destructive tools

Transparency / provenance15%70

HTTPS ✓
advertises protocol 2025-06-18

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.

Grade another server

We re-grade h2-papers.org on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — h2-papers.org grade A-

Share on X Open card image

https://wmcp.sh/mcp/grade/h2-papers.org

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade A-](https://wmcp.sh/mcp/grade/h2-papers.org/badge.svg)](https://wmcp.sh/mcp/grade/h2-papers.org)

HTML

<a href="https://wmcp.sh/mcp/grade/h2-papers.org"><img src="https://wmcp.sh/mcp/grade/h2-papers.org/badge.svg" alt="MCP Trust Grade A- · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.