paper-search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CINII_APP_ID | No | CiNii Research の appid。なしでも動作するが、継続利用には NII へのアプリケーション登録を推奨 | |
| PAPER_SEARCH_DATA_DIR | No | PDF・収集記録の保存先（デフォルト ./data） | ./data |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersA | 日英の学術論文を検索する。 languages(ja / en)に応じて arXiv・CiNii Research を検索し、 重複除去・ランキング済みの論文候補を返す。本文取得は行わない。 categories は分野フィルタ(例: cs.SE、cs.AI。arXiv のみ有効)。 1 データソースの障害は warnings として返し、検索全体は失敗しない。 |
| inspect_papersA | 複数論文の詳細メタデータと本文取得可能性を一括調査する。 search_papers が返した paper_id を渡す。ファイル保存は行わない。 fulltext.status: available / metadata_only / restricted / not_found / unknown。 |
| collect_papersA | 複数論文の本文 PDF を一括取得しローカル保存する。 公開・合法的に取得可能な本文のみ収集する。部分成功を許容し、 per-item の status(collected / already_collected / unavailable / restricted / failed)と理由を返す。 |
| get_collected_papersA | 収集済み論文のローカル情報(パス・SHA-256)を返す。 paper_ids を省略すると収集済み論文の一覧を返す。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: searching, inspecting metadata, collecting full-text, and listing collected papers. There is no overlap or ambiguity.
All tools follow a consistent verb_noun pattern: search_papers, inspect_papers, collect_papers, get_collected_papers. Naming is uniform and predictable.
With 4 tools, the set is well-scoped for the paper search and management workflow. Each tool serves a necessary step and none is redundant.
The workflow covers search, inspection, collection, and listing. A minor gap is the lack of a delete/remove operation for collected papers, but the core lifecycle is well covered.