cinii-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CINII_APPID | Yes | Your CiNii Web API application ID (required for API access) |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cinii_search_articlesA | Search CiNii Research for journal articles. Returns the unified envelope. CiNii matches catalogued metadata and ANDs a multi-word query, so an un-indexed compound returns zero even when related work exists — a ZERO_CONJUNCTION diagnostic marks this; vary the rendering rather than concluding the literature is absent. A SCRIPT_LATIN_QUERY diagnostic means the query searched romanized metadata only. The same string may behave very differently on J-STAGE (full text). Foundational monographs sit in cinii_search_books, not the article index.
|
| cinii_search_booksA | Search CiNii Research for books and monographs (NACSIS-CAT, NDL Search). Returns the unified envelope. A book can be looked up by |
| cinii_search_dissertationsB | Search CiNii Research for doctoral dissertations. Returns the unified envelope.
|
| cinii_search_kakenB | Search KAKEN (科研費) research projects. Returns the unified envelope (record_type 'project'). A project can be looked up by |
| cinii_search_allB | Cross-type search across all CiNii content. Returns the unified envelope. The cross search mixes types. Each record's type is taken from its own dc:type (article, book, dataset, dissertation, project, researcher); a record without one is reported as 'article'. |
| cinii_search_dataA | Search CiNii Research for research data (datasets). Returns the unified envelope. Covers data deposited through DataCite, JDCAT, IRDB, institutional data archives and, since 21 April 2026, research data recorded in KAKEN. Records are typed from their own dc:type, normally 'dataset'. |
| cinii_search_projects_and_productsB | Search KAKEN projects together with their research products (articles, books, data, dissertations) in one result set. Returns the unified envelope. Useful with |
| cinii_search_researchersA | Search for researchers in CiNii. Returns the unified envelope (record_type 'researcher'). Note: researcher affiliation is not carried by the record schema; the researcher name occupies the title field and the profile URL the ids.url_ja field. Researcher sorts: NAME_ASC/NAME_DESC, PROJECTS_DESC/PROJECTS_ASC, PRODUCTS_DESC/PRODUCTS_ASC, NEWEST, RELEVANCE. |
| cinii_get_holdingsA | List the libraries that hold a book or journal, by its NCID, from NACSIS-CAT through CiNii Research (/opensearch/holder, live since 30 March 2026). Returns the unified envelope (operation 'get_holdings', record_type 'holding'); each item names a library, its page, its NACSIS-CAT library ID (extra.library_id) and, where the library supplies one, a link into its own catalogue for this title (extra.catalog_url). Filters narrow the list to libraries that take ILL requests, offer copy or loan service, belong to Japan–US or Japan–Korea ILL, or (journals) hold a given year, volume or number. Zero holdings is HOLDINGS_NONE_REGISTERED, not proof that no library has the item. |
| cinii_search_librariesA | Find NACSIS-CAT member libraries by name (/opensearch/library, live since 30 March 2026). Returns the unified envelope (record_type 'library'); each item carries the library's NACSIS-CAT ID in extra.library_id, which cinii_get_holdings takes as library_id. |
| cinii_get_recordA | Fetch a single CiNii record by URL or CRID. Returns the unified envelope (operation 'get_record'). |
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 11 tools
Tools are partitioned mostly by record type (books, articles, dissertations, data, kaken, researchers, libraries, holdings), which gives clear primary boundaries. The main overlap is between cinii_search_all, cinii_search_kaken, and cinii_search_projects_and_products, which all return mixed/project records and require reading descriptions to choose correctly; well-written descriptions mitigate this rather than eliminate it.
Every tool follows the same cinii_<verb>_<noun> snake_case pattern: search_books, search_articles, get_holdings, get_record, etc. Verbs are used consistently (search_ for queries, get_ for single-resource fetches), so the convention is fully predictable.
Eleven tools map cleanly onto the distinct CiNii content types plus the two NACSIS-CAT auxiliary operations (holdings, libraries) and a single-record fetch. Each tool has a recognizable domain slice and none appear redundant enough to remove.
The surface covers search across all major record types, single-record retrieval by CRID/URL, ISBN/NCID lookup, library lookup, and holdings — a coherent discovery lifecycle. Minor gaps exist (no citation/export or bulk record retrieval, no explicit researcher-by-ID fetch aside from search), but agents can work around these.