{
  "markdown": "# @h2-papers/mcp-server\n\nModel Context Protocol (MCP) server for [**H2 Papers**](https://h2-papers.org/) — PubMed molecular hydrogen medical literature, structured in Japanese with per-paper safety notes inline.\n\n## Why\n\nWhen 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.\n\n## Tools (6, implemented in task #11)\n\n| Tool | Purpose |\n|---|---|\n| `search_h2_papers`    | Filter / sort / paginate the paper corpus. `safety_notes` inline on each item. |\n| `get_paper`           | Single paper detail. `safety_notes` always present. |\n| `get_safety_notes`    | Detail pages (LFL/UFL terminology, accident-case index, lineage). |\n| `get_topic_view`      | `/topics/{method}/{slug}` structured meta view for question-form queries. |\n| `get_lineage`         | The four-paper inhalation safety threshold lineage. |\n| `get_accident_cases`  | Consumer Affairs Agency accident records related to hydrogen inhalers. |\n\n## Citation policy\n\nCite results as `via H2 Papers` with the `_canonical` URL and the `pubmed_url`. **Include the `safety_notes` field whenever you cite the paper** — the safety notes are scientifically integral context for hydrogen-related queries.\n\n## Install (Smithery)\n\n```bash\nnpx -y @h2-papers/mcp-server\n```\n\nOr via Smithery YAML config in your MCP client of choice.\n\n## License\n\nMIT\n",
  "bytes": 1594,
  "sha": "bd9712be69ce6f6cd9821c89ead7f273607b31769582544d3906aa29321f13e2",
  "repo_slug": "h2-papers/h2-papers-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_h2_papers_mcp_server_1243b31d/readme"
}