@xbghc/zotero-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ZOTERO_API_KEY | Yes | Zotero API密钥 | |
| ZOTERO_USER_ID | Yes | 用户ID | |
| ZOTERO_GROUP_ID | No | 群组ID(可选) | |
| ZOTERO_MCP_CACHE_DIR | No | 附件缓存目录(可选) | |
| TRANSLATION_SERVER_URL | No | Translation Server地址(可选) |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_itemsA | Search items in the Zotero library.
|
| get_itemA | Get complete metadata of a single item by its key. Returns all fields: title, creators, abstract, DOI, URL, tags, collections, etc. Use this after search_items to get full details of a specific item. |
| get_recent_itemsA | Get the most recently added items in the Zotero library. Useful for checking what was recently imported or created. Returns items sorted by dateAdded in descending order. |
| get_item_childrenA | Get child items (attachments, notes) of a parent item.
|
| get_item_fulltextA | Get the full-text content of an item (usually a PDF attachment).
|
| get_trash_itemsA | Get items that have been moved to trash. Items in trash can be restored or permanently deleted from Zotero client. |
| get_saved_searchesA | Get saved searches (smart collections) defined in the Zotero library. Returns search names and their filter conditions. |
| list_collectionsA | List all collections (folders) in the Zotero library. Collections help organize items into hierarchical folders. Use parentKey to list sub-collections of a specific collection. |
| get_collection_itemsA | Get all items in a specific collection. Returns items directly in the collection (not in sub-collections). |
| create_collectionA | Create a new collection (folder) in the Zotero library. Collections help organize items into hierarchical folders. Use parentCollection to create a sub-collection. |
| update_collectionA | Update a collection's name or parent. Set parentCollection to false to move to top level. |
| delete_collectionA | Delete a collection from the library. Items in the collection are NOT deleted - they remain in the library. Sub-collections are also deleted. |
| list_tagsA | List all tags used in the Zotero library. Tags can be used with search_items to filter items. Type 0 = user-created tags, Type 1 = automatic tags. |
| create_itemA | Create a new item in the Zotero library with manual metadata entry. Common item types: journalArticle, book, bookSection, conferencePaper, webpage, thesis. For journal articles, use create_item_by_identifier with DOI instead - it's faster and more accurate. |
| create_item_by_identifierA | Create a new item by looking up metadata from DOI, ISBN, PMID, or arXiv ID. This is the preferred way to add published papers - metadata is fetched automatically. Requires Translation Server to be running (see README for setup). Examples: "10.1038/nature12373" (DOI), "978-0-13-468599-1" (ISBN), "PMID:12345678", "arXiv:2301.00001" |
| export_bibliographyA | Export items as formatted bibliography or citation data. Selection methods (use ONE):
Formats:
Common styles for bibliography: apa, chicago-author-date, ieee, vancouver, harvard Output: Content is always saved to a file (to avoid flooding the conversation with large exports). Returns file path and summary. |
| update_itemA | Update metadata fields of an existing item. Only provide fields you want to change - other fields remain unchanged. Common fields: title, date, DOI, url, abstractNote, publicationTitle, volume, issue, pages, extra. |
| delete_itemA | Move an item to trash (does not permanently delete). The item can be restored from trash in the Zotero client. To permanently delete, user must empty trash in Zotero. |
| add_tags_to_itemA | Add one or more tags to an existing item. Tags are useful for organizing and filtering items. Duplicate tags are automatically ignored. |
| add_item_to_collectionA | Add an item to a collection (folder). An item can belong to multiple collections. Use list_collections to get available collection keys. |
| download_attachmentA | Download an attachment file (PDF, etc.) to local cache.
|
| clear_attachment_cacheA | Clear cached attachment files to free disk space.
|
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 22 tools
Most tools target distinct resources and actions (e.g., get_item vs. get_item_fulltext vs. download_attachment). A few overlapping retrieval paths exist (search_items with includeTrashed vs. get_trash_items) but descriptions clarify their purposes.
All tool names use snake_case, but the verb pattern is inconsistent: 'get_' is used for both single items and lists (get_trash_items, get_recent_items) while 'list_' is reserved for collections/tags. This mix of get/list for list-style operations makes naming less predictable.
At 22 tools, the count is in the 'heavy' range (16-25) and feels borderline. Each tool has a distinct purpose, but the breadth may overwhelm agents; some operations could be consolidated (e.g., tag and collection membership updates).
Core CRUD for items and collections is covered, and there are useful extras like full-text search and bibliography export. However, notable gaps remain: no tool to remove tags from an item, remove an item from a collection, or restore items from trash. These missing operations could cause agent failures in common workflows.