zotero-mcp
MCP server that connects to a local Zotero library, enabling search, citation generation with CSL styles, and automatic bibliography updates in Markdown documents.
README
zotero-mcp
Antigravity plugin that adds an MCP server connected to your local Zotero library to:
- Search items in your library (by text, type and collection).
- Cite with CSL styles: APA, MLA, Chicago (author-date), Harvard, IEEE and Vancouver.
- Auto-update bibliographies: add a new citation and the document's references section regenerates automatically.
Installable from GitHub with:
agy plugin install https://github.com/Robernetes/zotero-mcp
What can the AI do with this MCP?
- Answer questions about your library: search for sources on a topic, filter by type (articles, books, theses) or collection, and get full details of any item (abstract, authors, year, URL, DOI).
- Cite correctly: generate in-text citations with the right style (APA, MLA, Chicago, Harvard, IEEE, Vancouver) and language (es-ES, en-US), with page locators (
(Author, 2020, p. 15)), prefixes and suffixes. - Write academic documents with real references: the AI inserts citations and keeps the bibliography synced: add citations with
zotero_citeand the document's references section regenerates withzotero_bibliography. - Verify sources: never invents references; every item is validated against Zotero before citing.
- Diagnostics:
zotero_statustells you whether Zotero is available.
Limits (v1): read-only access to the Zotero library (cannot add/edit/delete items).
Requirements
- Zotero installed and open, with the setting "Allow other applications on this computer to communicate with Zotero" enabled (Edit → Settings → Advanced). The server uses the local API (port 23119), no API key needed.
- Node.js ≥ 18 (tested with Node 24).
Installation
agy plugin install https://github.com/Robernetes/zotero-mcp
If the plugin doesn't run dependency installation automatically:
git clone https://github.com/Robernetes/zotero-mcp
cd zotero-mcp
npm install # or: powershell -File scripts/setup.ps1 / sh scripts/setup.sh
Configuration
The server works out of the box (default values). Optional variables
(defined in .env.example; passed to the server via mcp_config.json with ${VAR}):
| Variable | Default | Description |
|---|---|---|
ZOTERO_API_URL |
http://127.0.0.1:23119/api |
Zotero local API URL |
ZOTERO_DEFAULT_STYLE |
apa |
Default CSL style |
ZOTERO_LOCALE |
es-ES |
Default style locale |
MCP Tools
| Tool | Description |
|---|---|
zotero_status |
Check connection to the local API. |
zotero_search |
Search items (query, qmode, itemType, collectionKey, limit, sort, direction). |
zotero_get_item |
Full item details by key. |
zotero_list_collections |
List collections. |
zotero_cite |
Textual citation (key, style, locale, locator, label, prefix, suffix, register). |
zotero_bibliography |
Bibliography from registered citations or explicit keys; with filePath + apply: true updates the references section of a .md file. |
zotero_read_docx |
Read paragraphs from a .docx (index, text, whether it already has Zotero fields). |
zotero_insert_citation_docx |
Insert an ADDIN ZOTERO_ITEM CSL_CITATION field at the end of a paragraph in a .docx. |
zotero_update_bibliography_docx |
Insert or update the ADDIN ZOTERO_BIBL field in a .docx. |
Usage examples (JSON)
Examples use placeholder Zotero keys (ABC12345, DEF67890); replace with real keys
from zotero_search output.
1. Check connection
{ "tool": "zotero_status" }
{ "ok": true, "baseUrl": "http://127.0.0.1:23119/api", "library": "local (users/0)" }
2. Search items
{ "tool": "zotero_search", "args": { "query": "artificial intelligence", "limit": 10 } }
Additional filters: itemType (journalArticle, book, thesis, conferencePaper…),
collectionKey (from zotero_list_collections), sort/direction. Empty query = list all.
3. Item details
{ "tool": "zotero_get_item", "args": { "key": "ABC12345" } }
4. List collections
{ "tool": "zotero_list_collections" }
5. Cite
{ "tool": "zotero_cite", "args": { "key": "ABC12345", "style": "apa", "locale": "en-US" } }
→ (Author, 2020)
With exact page:
{ "tool": "zotero_cite", "args": { "key": "ABC12345", "style": "apa", "locator": "15", "label": "page" } }
→ (Author, 2020, p. 15)
With prefix/suffix:
{ "tool": "zotero_cite", "args": { "key": "ABC12345", "style": "apa", "prefix": "see ", "suffix": ", for a full analysis" } }
With register: false the citation is generated but not added to the bibliography.
6. Bibliography (auto-updating)
From registered citations (recommended):
{ "tool": "zotero_bibliography", "args": { "style": "apa", "locale": "en-US" } }
From explicit keys (without affecting the register):
{ "tool": "zotero_bibliography", "args": { "keys": ["ABC12345", "DEF67890"], "style": "ieee" } }
Update the references section of a Markdown document (with diff preview):
{ "tool": "zotero_bibliography", "args": { "filePath": "C:/docs/paper.md", "dryRun": true } }
Write the file:
{ "tool": "zotero_bibliography", "args": { "filePath": "C:/docs/paper.md", "apply": true } }
If the document has no references section, create it at the end with createSection: true
(uses the heading ## Bibliography). Output formats: plaintext, markdown (default), html.
Complete typical flow
zotero_search { "query": "artificial intelligence" }→ get the item'skey.zotero_cite { "key": "ABC12345", "style": "apa" }→ insert(Author, 2020)in the text.zotero_bibliography { "filePath": "C:/docs/paper.md", "apply": true }→ regenerate the## Bibliography(orReferences,Works Cited, etc.) section with all registered citations.
The bibliography stays updated automatically: just add a citation with zotero_cite and call
zotero_bibliography again. To review before writing, omit apply (dryRun mode returns the diff).
7. Read a Word document structure
{ "tool": "zotero_read_docx", "args": { "filePath": "C:/docs/paper.docx" } }
→ { paragraphs: [{ index: 0, text: "Lorem ipsum...", hasZoteroField: false }, ...] }
8. Insert a citation in Word (dynamic Zotero field)
{ "tool": "zotero_insert_citation_docx", "args": { "filePath": "C:/docs/paper.docx", "key": "ABC12345", "paragraphIndex": 0, "style": "apa", "apply": true } }
With locator:
{ "tool": "zotero_insert_citation_docx", "args": { "filePath": "C:/docs/paper.docx", "key": "ABC12345", "paragraphIndex": 2, "locator": "15", "label": "page", "apply": true } }
9. Update bibliography in Word
{ "tool": "zotero_update_bibliography_docx", "args": { "filePath": "C:/docs/paper.docx", "style": "apa", "apply": true } }
The citation is inserted as an ADDIN ZOTERO_ITEM CSL_CITATION field with the item's CSL JSON. When the .docx is opened in Word with the Zotero plugin, the citation renders correctly and the bibliography updates automatically.
Typical Word flow
zotero_read_docx→ learn the structure (paragraphs and their indices).- For each citation:
zotero_insert_citation_docxat the correct paragraph. zotero_update_bibliography_docx→ adds/updates the BIBL field at the end.
Included skill
zotero-research teaches the agent when and how to use each tool (search, citation and
bibliography maintenance). It activates automatically when the user asks to search, cite or update bibliographies.
Included styles and locales
- CSL styles (CC-BY-SA 3.0 from the citation-style-language/styles project):
apa,mla,chicago-author-date,harvard-cite-them-right,ieee,vancouver. - Locales (CC-BY-SA 3.0 from citation-style-language/locales):
es-ES,en-US.
To add styles or locales, place the file in src/csl/ or src/locales/ with the correct name.
Security
- Read-only access to the Zotero library: the MCP does not add, edit or delete items.
- The only write operations are the references section of Markdown files and Zotero fields in Word files (.docx), and only with explicit
apply: true. - No secrets in the repository; credentials (if any) go through environment variables.
- Parameter validation, connection timeout (8 s) and file size limit (2 MB).
Troubleshooting
| Symptom | Cause | Solution |
|---|---|---|
zotero_status → ok: false |
Zotero closed or local API disabled | Open Zotero and enable "Allow other applications on this computer to communicate with Zotero" (Edit → Settings → Advanced). No restart required. |
zotero_cite → "Item not found with key..." |
Wrong key or deleted item | Search again with zotero_search and copy the exact key. |
zotero_bibliography → "Unsupported style" |
Style not included | Use one of: apa, mla, chicago-author-date, harvard-cite-them-right, ieee, vancouver (or add the .csl file to src/csl/). |
| "No references section found" | Document has no bibliography heading | Pass createSection: true to create it at the end. |
| "filePath must be a .md file..." | .docx or other extension was passed |
v1 only updates Markdown (.md/.markdown). |
| Numeric citations "reset" | Style changed mid-document | Use the same style/locale throughout the document (changing style resets numbering). |
Development
npm test # test suite (node --test)
npm start # start the MCP server via stdio
node scripts/smoke.mjs # MCP handshake + list registered tools
node scripts/e2e.mjs '{"tool":"zotero_status"}' '{"tool":"zotero_search","args":{"query":"x"}}' # test tools against your Zotero
The structure follows the complete Antigravity plugin pattern
(plugin.json, mcp_config.json, server/ → src/, skills/, scripts/).
License
MIT — see LICENSE. CSL styles and locales are CC-BY-SA 3.0 (see "Included styles and locales").
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。