DocuSky MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOCUSKY_TIMEOUT | No | 單次請求逾時（秒），預設為 120 | |
| DOCUSKY_BASE_URL | No | API 根路徑，預設為 https://docusky.org.tw/DocuSky/webApi | |
| DOCUSKY_PASSWORD | No | 你的 DocuSky 密碼（選填，留空則僅查詢公開資料庫） | |
| DOCUSKY_USERNAME | No | 你的 DocuSky 帳號（選填，留空則僅查詢公開資料庫） | |
| DOCUSKY_CREDENTIALS | No | 憑證檔位置（給非 Claude Desktop 的 MCP 客戶端用的後備），預設為 ~/.docusky/credentials.json |
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 |
|---|---|
| list_databasesA | List DocuSky databases available to this server. Args: target: "OPEN" for public databases, "USER" for the logged-in account's own. include_friend_db: Also list databases shared by DocuSky "friends" (USER only). |
| list_corporaA | List the corpora inside one database, with document counts. Args: db: Database title, exactly as returned by list_databases. target: "OPEN" or "USER". include_friend_db: Include databases shared by friends (USER only). |
| search_documentsA | Full-text search one DocuSky database; returns metadata plus a short excerpt per hit. Full document text is deliberately omitted — call get_document with a hit's
Args:
db: Database title.
query: Search terms. |
| get_documentA | Fetch the full text of one search hit, identified by its position in the result set.
Long documents are returned in slices: raise Args: db: Database title. result_number: 1-based rank of the document within the query's results. query: The same query string used in search_documents. corpus: The same corpus used in search_documents. target: "OPEN" or "USER". page_size: The same page_size used in search_documents. offset: Character offset into the document body. max_chars: Maximum characters of body text to return. include_raw_xml: Also return the untouched DocuXML content. owner_username: Owner of a friend-shared database, when applicable. |
| post_classificationA | Break a query's hits down by DocuSky's post-classification facets. Returns, per facet (corpus, period, place, category…), a distribution of [value, document count, hit count] — the quickest way to see how a term is spread across a database. Args: db: Database title. query: Search terms, or ".all" for the whole database. corpus: Corpus title, or "[ALL]". target: "OPEN" or "USER". owner_username: Owner of a friend-shared database, when applicable. |
| tag_analysisA | Summarize the DocuXML tags (people, places, dates, custom markup) in a query's hits. Only meaningful for databases whose documents carry inline tagging; returns an empty result otherwise. Args: db: Database title. query: Search terms, or ".all" for the whole database. corpus: Corpus title, or "[ALL]". target: "OPEN" or "USER". owner_username: Owner of a friend-shared database, when applicable. |
| check_loginA | Report whether DocuSky credentials are configured and whether they work. Public databases need no login; run this only when private ("USER") databases are unreachable. |
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 7 tools
Each tool has a clearly distinct purpose: listing databases, listing corpora, checking login, searching documents, fetching full text, post-classification breakdown, and tag analysis. No two tools overlap significantly; the workflow is well-defined with search_documents and get_document having complementary roles.
All tool names follow a consistent snake_case verb_noun pattern (list_databases, list_corpora, check_login, search_documents, get_document, post_classification, tag_analysis). The pattern is predictable and readable throughout.
Seven tools form a well-scoped, cohesive set that covers the core operations for exploring and analyzing DocuSky databases without redundancy. Each tool earns its place in the workflow.
The toolset covers the essential lifecycle: discovery (list databases/corpora), authentication (check_login), search (search_documents), retrieval (get_document), and analysis (post_classification, tag_analysis). While read-only operations are comprehensive, there is no support for modifying or creating databases/corpora, which may be a deliberate scope limitation.