io.github.h2-papers/mcp-server (MCP)

Model Context Protocol (MCP) server for H2 Papers. It provides PubMed molecular-hydrogen medical literature, structured in Japanese, and includes delivery-aware safety notes inline. The server is designed so that safety context is returned together with paper results rather than requiring an extra request.

🛠️ Key Features

PubMed molecular-hydrogen medical literature access
Japanese-structured content
Inline, delivery-method-aware safety notes returned with results
Provides 6 tools

🚀 Use Cases

Answering questions about hydrogen-related therapy using paper evidence
Handling topics related to water or inhalation with safety context included in the same response
Supporting agent workflows where safety notes must accompany each paper output

⚡ Developer Benefits

Tool outputs include safety_notes in the same JSON object as paper-returned data
Avoids follow-up calls to retrieve safety context

⚠️ Limitations

Scope is limited to PubMed molecular-hydrogen medical literature and delivery-aware safety notes for that context

{ "type": "object", "properties": { "q": { "type": "string", "description": "Free-text query (Japanese or English)." }, "delivery_method": { "type": "string", "enum": [ "inhalation", "hydrogen_water", "injection", "bath", "topical", "animal", "in_vitro", "mixed", "na" ] }, "effect_reported": { "type": "string", "enum": [ "positive", "null", "mixed", "adverse", "not_assessed" ] }, "study_type": { "type": "string", "enum": [ "human_rct", "human_observational", "human_case", "animal", "in_vitro", "review", "meta_analysis", "letter", "other" ] }, "year_min": { "type": "integer" }, "year_max": { "type": "integer" }, "lineage_only": { "type": "boolean", "description": "Restrict to the four-paper inhalation safety threshold lineage." }, "include_predatory": { "type": "boolean" }, "lang": { "type": "string", "enum": [ "ja", "en" ], "description": "Response language (default ja)" }, "limit": { "type": "integer", "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "minimum": 0 } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" }

{ "type": "object", "properties": { "pmid": { "type": "string", "pattern": "^\\d{1,9}$", "description": "PubMed identifier" }, "lang": { "type": "string", "enum": [ "ja", "en" ] } }, "required": [ "pmid" ], "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" }

{ "type": "object", "properties": { "slug": { "type": "string", "enum": [ "inhalation-concentration", "accident-cases", "lfl-ufl-explained", "lineage" ], "description": "When omitted, returns the index of all safety-notes pages." }, "lang": { "type": "string", "enum": [ "ja", "en" ] } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" }

{ "type": "object", "properties": { "method": { "type": "string", "enum": [ "inhalers", "hydrogen-water", "injection", "bath", "topical" ], "description": "When omitted, returns the index of all topics." }, "slug": { "type": "string", "description": "Topic slug under the chosen method (e.g. \"safety\", \"evidence\", \"clinical-applications\")." }, "lang": { "type": "string", "enum": [ "ja", "en" ] } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" }

{ "type": "object", "properties": { "lang": { "type": "string", "enum": [ "ja", "en" ] } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" }

Why

When an AI agent answers a question about hydrogen-related therapy, water, or inhalation, the response should carry both the paper evidence and the delivery-method-aware safety context. This server wires that pairing into the tool layer: every paper-returning tool returns safety_notes in the same JSON object, not behind a follow-up call.

Tools (6, implemented in task #11)

Tool

Purpose

search_h2_papers

Filter / sort / paginate the paper corpus. safety_notes inline on each item.

get_paper

Single paper detail. safety_notes always present.

get_safety_notes

Detail pages (LFL/UFL terminology, accident-case index, lineage).

get_topic_view

/topics/{method}/{slug} structured meta view for question-form queries.

get_lineage

The four-paper inhalation safety threshold lineage.

get_accident_cases

Consumer Affairs Agency accident records related to hydrogen inhalers.

Install

Tools (6)

search_h2_papersget_paperget_safety_notesget_topic_viewget_lineageget_accident_cases

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@h2-papers/mcp-server@0.1.0"
      ]
    }
  }
}

水素分子医学文献データベース — Molecular hydrogen medical literature (H2 Papers)

io.github.h2-papers/mcp-server (MCP)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search_h2_papers

get_paper

get_safety_notes

get_topic_view

get_lineage

get_accident_cases

@h2-papers/mcp-server

Why

Tools (6, implemented in task #11)

Citation policy

Install (Smithery)

License

Install

Related servers

q	string	optional	Free-text query (Japanese or English).
delivery_method	string	optional
effect_reported	string	optional
study_type	string	optional
year_min	integer	optional
year_max	integer	optional
lineage_only	boolean	optional	Restrict to the four-paper inhalation safety threshold lineage.
include_predatory	boolean	optional
lang	string	optional	Response language (default ja)
limit	integer	optional
offset	integer	optional

slug	string	optional	When omitted, returns the index of all safety-notes pages.
lang	string	optional

method	string	optional	When omitted, returns the index of all topics.
slug	string	optional	Topic slug under the chosen method (e.g. "safety", "evidence", "clinical-applications").
lang	string	optional