zotero-mcp
It's a plugin extension in Zotero. Zotero MCP Plugin enables integration between AI assistants and Zotero through MCP. Zotero MCP Plugin 是一个 Zotero 插件,通过 MCP协议实现 AI 助手与 Zotero深度集成。插件支持文献检索、元 数据管理、全文分析和智能问答等功能,让 Claude、ChatGPT 等 AI 工具能够直接访问和操作您的文献库。
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/cookjohn/zotero-mcp with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/cookjohn/zotero-mcp'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/cookjohn--zotero-mcp)HTML
<a href="/listings/cookjohn--zotero-mcp"><img src="/api/listings/cookjohn--zotero-mcp/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
This guide is intended to help general users quickly configure and use Zotero MCP, enabling your AI assistant to work seamlessly with your Zotero library.
1. Installation (For General Users)
**What is Zotero MCP?**
Simply put, Zotero MCP is a bridge connecting your AI client (like Cherry Studio, Gemini CLI, Claude Desktop, etc.) and your local Zotero reference management software. It allows your AI assistant to directly search, query, and cite references from your Zotero library, greatly enhancing academic research and writing efficiency.
**Two-Step Quick Start:**
1. **Install the Plugin**: * Go to the project's [Releases Page](https://github.com/cookjohn/zotero-mcp/releases) to download the latest `zotero-mcp-plugin-x.x.x.xpi` file. * In Zotero, install the `.xpi` file via `Tools -> Add-ons`. * Restart Zotero.
2. **Configure the Plugin**: * In Zotero's `Preferences -> Zotero MCP Plugin` tab, configure your connection settings: - **Enable Server**: Start the integrated MCP server - **Port**: Default is `23120` (you can change this if needed) - **Generate Client Configuration**: Click this button to get configuration for your AI client
---
2. Connect to AI Clients
**Important**: The Zotero plugin now includes an **integrated MCP server** that uses the Streamable HTTP protocol. No separate server installation is needed.
Streamable HTTP Connection
The plugin uses Streamable HTTP, which enables real-time bidirectional communication with AI clients:
1. **Enable Server** in the Zotero plugin preferences 2. **Generate Client Configuration** by clicking the button in plugin preferences 3. **Copy the generated configuration** to your AI client
Supported AI Clients
- **Claude Desktop**: Streamable HTTP MCP support - **Cherry Studio**: Streamable HTTP support - **Cursor IDE**: Streamable HTTP MCP support - **Custom implementations**: Streamable HTTP protocol
For detailed client-specific configuration instructions, see the [Chinese README](./README-zh.md).
---
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 406 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Zotero MCP - Model Context Protocol Integration for Zotero
- Zotero MCP is an open-source project designed to seamlessly integrate powerful AI capabilities with the leading reference management tool, Zotero, through the Model Context Protocol (MCP). This project consists of two core components: a Zotero plugin and an MCP server, which work together to provide AI assistants (like Claude) with the ability to interact with your local Zotero library.
- _This README is also available in: [:cn: 简体中文](./README-zh.md) | :gb: English._
- [](https://github.com/cookjohn/zotero-mcp)
- [](https://www.zotero.org)
- [](https://nodejs.org)
- [](https://www.typescriptlang.org)
- []()
- [](README.md)
- [](README-zh.md)
- ---
- ## Fork us on Wechat
- | MP | Forum |
- | :--- | :---: |
- |  |  |
- ## 📚 Project Overview
- The Zotero MCP server is a tool server based on the Model Context Protocol that provides seamless integration with the Zotero reference management system for AI applications like Claude Desktop. Through this server, AI assistants can:
- - 🔍 **Smart Search**: Multi-dimensional library search (title/creator/year/tags/fulltext/semantic) with boolean operators and relevance scoring
- - 📖 **Content Extraction**: Extract PDF full-text, notes, abstracts, webpage snapshots with fine-grained mode control
- - 📝 **Annotation Analysis**: Search and analyze PDF highlights and annotations by color, tags, and keywords
- - 📂 **Collection Browsing**: Browse and search collection hierarchies, retrieve items within collections
- - 🧠 **Semantic Search**: AI-powered concept matching via embedding vectors, discover related literature across languages
- - ✏️ **Write Operations**: Create notes, manage tags, update metadata, create new items and attach PDFs
- - 💾 **Full-text Database**: Access and search cached PDF full-text content
- This enables AI assistants to help you with literature reviews, citation management, content analysis, annotation organization, knowledge base management, and more.
- ## 🚀 Project Structure
- This project now features a **unified architecture** with an integrated MCP server:
- - **`zotero-mcp-plugin/`**: A Zotero plugin with **integrated MCP server** that communicates directly with AI clients via Streamable HTTP protocol
- - **`IMG/`**: Screenshots and documentation images
- - **`README.md`** / **`README-zh.md`**: Documentation files
- **Unified Architecture:**
- ```
- AI Client ↔ Streamable HTTP ↔ Zotero Plugin (with integrated MCP server)
- ```
- This eliminates the need for a separate MCP server process, providing a more streamlined and efficient integration.
- ---
- ## 🚀 Quick Start Guide
- This guide is intended to help general users quickly configure and use Zotero MCP, enabling your AI assistant to work seamlessly with your Zotero library.
- ### 1. Installation (For General Users)
- **What is Zotero MCP?**
- Simply put, Zotero MCP is a bridge connecting your AI client (like Cherry Studio, Gemini CLI, Claude Desktop, etc.) and your local Zotero reference management software. It allows your AI assistant to directly search, query, and cite references from your Zotero library, greatly enhancing academic research and writing efficiency.
- **Two-Step Quick Start:**
- 1. **Install the Plugin**:
- * Go to the project's [Releases Page](https://github.com/cookjohn/zotero-mcp/releases) to download the latest `zotero-mcp-plugin-x.x.x.xpi` file.
- * In Zotero, install the `.xpi` file via `Tools -> Add-ons`.
- * Restart Zotero.
- 2. **Configure the Plugin**:
- * In Zotero's `Preferences -> Zotero MCP Plugin` tab, configure your connection settings:
- - **Enable Server**: Start the integrated MCP server
- - **Port**: Default is `23120` (you can change this if needed)
- - **Generate Client Configuration**: Click this button to get configuration for your AI client
- ---
- ### 2. Connect to AI Clients
- **Important**: The Zotero plugin now includes an **integrated MCP server** that uses the Streamable HTTP protocol. No separate server installation is needed.
- #### Streamable HTTP Connection
- The plugin uses Streamable HTTP, which enables real-time bidirectional communication with AI clients:
- 1. **Enable Server** in the Zotero plugin preferences
- 2. **Generate Client Configuration** by clicking the button in plugin preferences
- 3. **Copy the generated configuration** to your AI client
- #### Supported AI Clients
- - **Claude Desktop**: Streamable HTTP MCP support
- - **Cherry Studio**: Streamable HTTP support
- - **Cursor IDE**: Streamable HTTP MCP support
- - **Custom implementations**: Streamable HTTP protocol
- For detailed client-specific configuration instructions, see the [Chinese README](./README-zh.md).
- ---
- ## 👨💻 Developer Guide
- ### Prerequisites
- - **Zotero** 7.0 or higher
- - **Node.js** 18.0 or higher
- - **npm** or **yarn**
- - **Git**
- ### Step 1: Install and Configure the Zotero Plugin
- 1. Download the latest `zotero-mcp-plugin.xpi` from the [Releases Page](https://github.com/cookjohn/zotero-mcp/releases).
- 2. Install it in Zotero via `Tools -> Add-ons`.
- 3. Enable the server in `Preferences -> Zotero MCP Plugin`.
- ### Step 2: Development Setup
- 1. Clone the repository:
- ```bash
- git clone https://github.com/cookjohn/zotero-mcp.git
- cd zotero-mcp
- ```
- 2. Set up the plugin development environment:
- ```bash
- cd zotero-mcp-plugin
- npm install
- npm run build
- ```
- 3. Load the plugin in Zotero:
- ```bash
- # For development with auto-reload
- npm run start
- # Or install the built .xpi file manually
- npm run build
- ```
- ### Step 3: Connect AI Clients (Development)
- The plugin includes an integrated MCP server that uses Streamable HTTP:
- 1. **Enable the server** in Zotero plugin preferences
- 2. **Generate client configuration** using the plugin's built-in generator
- 3. **Configure your AI client** with the generated Streamable HTTP configuration
- Example configuration for Claude Desktop:
- ```json
- {
- "mcpServers": {
- "zotero": {
- "transport": "streamable_http",
- "url": "http://127.0.0.1:23120/mcp"
- }
- }
- }
- ```
- ---
- ## 🧩 Features
- ### `zotero-mcp-plugin` Features
- - **Integrated MCP Server**: Built-in MCP server using Streamable HTTP protocol, no separate process needed
- - **Advanced Search Engine**: Full-text search with boolean operators, relevance scoring, filtering by title, creator, year, tags, item type, and more
- - **Unified Content Extraction**: Extract content from PDFs, attachments, notes, abstracts, webpage snapshots with four modes (minimal/preview/standard/complete)
- - **Smart Annotation System**: Search and retrieve PDF highlights, annotations, and notes by color, tags, and keywords with intelligent ranking
- - **Collection Management**: Browse, search collection hierarchies, get collection details, subcollections, and item lists
- - **Semantic Search**: AI-powered semantic search using embedding vectors
- - Supports OpenAI and Ollama embedding APIs (auto-detection)
- - Vector indexing with SQLite-vec storage
- - Index status column in main library view
- - Collection/item context menu for index management
- - **Write Operations**: Create/modify notes, manage tags, update metadata fields, create new items and reparent standalone PDFs
- - **Full-text Database**: Cached PDF full-text database with list, search, get, and stats operations
- - **Standalone Attachment Management**: Search and manage standalone PDF items without parent metadata
- - **Client Configuration Generator**: Automatically generates configuration for various AI clients
- - **Security**: Local-only operation ensuring complete data privacy
- - **User-Friendly**: Easy configuration through Zotero preferences interface
- ---
- ## 📸 Screenshots
- Here are some screenshots demonstrating the functionality of Zotero MCP:
- | Feature | Screenshot |
- | :--- | :---: |
- | **Feature Demonstration** |  |
- | **Literature Search** |  |
- | **Viewing Metadata** |  |
- | **Full-text Reading 1** |  |
- | **Full-text Reading 2** |  |
- | **Searching Attachments (Gemini CLI)** |  |
- | **Reading PDF (Gemini CLI)** |  |
- ---
- ## 🔧 API Reference (MCP Tools)
- The integrated MCP server provides **32 tools** in 6 categories:
- ### 1. Search & Query (7 tools)
- #### `search_library`
- Advanced library search with multi-dimensional filtering, boolean operators, relevance scoring, and intelligent mode control.
- - `q`, `title`, `titleOperator`, `yearRange`, `fulltext`, `fulltextMode`, `itemType`, `includeAttachments`, `mode` (minimal/preview/standard/complete), `relevanceScoring`, `sort`, `limit`, `offset`
- #### `search_annotations`
- Search annotations by query, colors, or tags with intelligent ranking.
- - `q`, `itemKeys`, `types` (note/highlight/annotation/ink/text/image), `colors`, `tags`, `mode`, `limit`, `offset`
- #### `search_fulltext`
- Full-text search across all document content with context snippets.
- - `q` (required), `itemKeys`, `mode`, `contextLength`, `caseSensitive`
- #### `search_collections`
- Search collections by name. Params: `q`, `limit`.
- #### `get_item_details`
- Get complete metadata for a single item. Params: `itemKey` (required), `mode`.
- #### `get_item_abstract`
- Get item abstract/summary. Params: `itemKey` (required), `format` (json/text).
- #### `get_content`
- Unified content extraction: PDF full-text, notes, abstracts, webpage snapshots from items or specific attachments.
- - `itemKey`, `attachmentKey`, `mode`, `include` (pdf/attachments/notes/abstract/webpage), `contentControl`, `format` (json/text)
- ### 2. Collection Management (4 tools)
- #### `get_collections`
- Get all collections. Params: `mode`, `limit`, `offset`.
- #### `get_collection_details`
- Get details of a specific collection. Params: `collectionKey` (required).
- #### `get_collection_items`
- Get items in a collection. Params: `collectionKey` (required), `limit`, `offset`.
- #### `get_subcollections`
- Get subcollections. Params: `collectionKey` (required), `limit`, `offset`, `recursive`.
- ### 3. Semantic Search (3 tools, can be disabled in preferences)
- #### `semantic_search`
- AI-powered semantic search using embedding vectors. Finds conceptually related content even without exact keyword matches.
- - `query` (required), `topK`, `minScore`, `language` (zh/en/all)
- #### `find_similar`
- Find items semantically similar to a given item.
- - `itemKey` (required), `topK`, `minScore`
- #### `semantic_status`
- Get semantic search service status and index statistics. No parameters required.
- ### 4. Full-text Database (1 tool)
- #### `fulltext_database`
- Access cached full-text content database (read-only).
- - `action` (required: list/search/get/stats), `query`, `itemKeys`, `limit`
- ### 5. Write Operations (6 tools, can be disabled in preferences)
- #### `write_note`
- Create or modify Zotero notes. Supports Markdown auto-conversion to HTML.
- - `action` (required: create/update/append), `parentKey`, `noteKey`, `content` (required), `tags`
- #### `write_tag`
- Add, remove, or replace tags on items.
- - `action` (required: add/remove/set), `itemKey` (required), `tags` (required)
- #### `write_metadata`
- Update metadata fields on items (title, abstract, date, DOI, creators, etc.).
- - `itemKey` (required), `fields`, `creators`
- #### `write_item`
- Create new items, reparent existing attachments, or import local files as attachments.
- - `action` (required: create/reparent/import), `itemType`, `fields`, `creators`, `tags`, `attachmentKeys`, `parentKey`, `filePath`, `parentItemKey`, `title`, `linkMode` (import: `imported_file` copies into Zotero storage, `linked_file` links in place — personal library only), `libraryID`
- #### `add_by_identifier`
- Import items by identifier (DOI, arXiv, ISBN, PMID, ADS bibcode) using Zotero's native resolvers — the same pipeline as the desktop "magic wand", including translator metadata and automatic attachment fetching.
- - `identifiers` (required), `libraryID`, `collectionKey`, `saveAttachments`, `duplicates`, `titleDuplicates`, `dryRun`, `async`, `jobID`
- #### `trash_item`
- Move one or more items to Zotero Trash. Items stay recoverable until the user empties Trash; permanent deletion is not supported (`permanent` is rejected).
- - `itemKeys` (required, array of item keys; deduplicated), `libraryID`
- ### 6. Citation & Bibliography (3 tools)
- #### `export_bibliography`
- Export one or more Zotero items as BibLaTeX/BibTeX (or CSL-JSON/CSL-YAML) entries powered by the zotero-better-bibtex (BBT) plugin. Requires Better BibTeX to be installed and running in Zotero.
- - `itemKeys` (required), `format` (biblatex/bibtex/csljson/cslyaml), `libraryID`
- #### `get_citation`
- Generate a formatted reference (bibliography entry) or in-text citation for one or more items using a CSL citation style. If no style is specified, uses the Zotero default Quick Copy style. Works without Better BibTeX.
- - `itemKeys` (required), `style`, `contentType` (html/text), `mode` (bibliography/citation), `libraryID`
- #### `list_citation_styles`
- List CSL citation styles available in Zotero (for use with `get_citation`).
- - `filter`
- ---
- ## 🔌 External Tool Registration API
- Other Zotero plugins can register custom MCP tools that are exposed through this plugin's MCP server. This allows third-party plugins to extend the AI-accessible toolset without running their own HTTP server.
- ### How It Works
- 1. Your plugin calls `Zotero.ZoteroMCP.api.registerTool(...)` to register a tool.
- 2. The tool appears in `tools/list` alongside built-in tools.
- 3. When an AI client calls the tool, the MCP server dispatches the call to your handler.
- 4. On disable/uninstall, call `Zotero.ZoteroMCP.api.unregisterTool(...)` or `unregisterAllTools(pluginID)`.
- ### API Methods
- | Method | Description |
- |---|---|
- | `registerTool(def)` | Register a custom MCP tool. Throws on invalid input or name collision. |
- | `unregisterTool(name)` | Unregister a tool by name. Returns `true` if removed. |
- | `unregisterAllTools(pluginID)` | Unregister all tools from a specific plugin. Returns count removed. |
- | `getRegisteredTools()` | List registered tools (readonly, handler excluded). |
- | `isToolRegistered(name)` | Check if a tool name is already registered. |
- | `onToolListChanged(cb)` | Subscribe to tool list changes. Returns an unsubscribe function. |
- ### Tool Definition
- ```typescript
- {
- name: string; // Unique, matches /^[a-z][a-z0-9_]*$/, must not collide with built-in tools
- description: string; // Shown to AI clients
- inputSchema: object; // JSON Schema for input parameters
- handler: (args: any) => Promise<any> | any; // Called when AI invokes the tool
- pluginID?: string; // Optional: your plugin ID (for bulk cleanup)
- enabled?: boolean; // Optional: visibility toggle (default: true)
- }
- ```
- ### Example (from another plugin)
- ```javascript
- // Register a custom MCP tool from your Zotero plugin
- const mcp = Zotero.ZoteroMCP;
- if (mcp && mcp.api && mcp.api.registerTool) {
- mcp.api.registerTool({
- name: 'my_plugin_count_items',
- description: 'Count items in the Zotero library by type',
- inputSchema: {
- type: 'object',
- properties: {
- itemType: { type: 'string', description: 'Filter by item type (e.g. journalArticle)' }
- }
- },
- handler: async (args) => {
- const items = await Zotero.Items.getAll(Zotero.Libraries.userLibraryID);
- const filtered = args.itemType
- ? items.filter(i => i.itemType === args.itemType)
- : items;
- return { total: filtered.length, itemType: args.itemType || 'all' };
- },
- pluginID: 'my-plugin@example.com'
- });
- }
- ```
- ### Cleanup on Uninstall
- ```javascript
- // In your plugin's shutdown hook:
- const mcp = Zotero.ZoteroMCP;
- if (mcp && mcp.api && mcp.api.unregisterAllTools) {
- mcp.api.unregisterAllTools('my-plugin@example.com');
- }
- ```
- ### Notes
- - Tool names must not collide with built-in tools (see list above). Use a prefix like `my_plugin_*`.
- - The registry survives MCP server restarts (e.g. port changes). Tools registered before the server starts will appear once it does.
- - Handler errors are caught and returned as MCP error responses — no need to wrap in try/catch.
- - Results are JSON-serialised and wrapped in MCP `text` content automatically.
- - External tools are **not** covered by this plugin's "Enable write operations" switch. If your tool modifies the library, gate it in your own plugin.
- - Registrations live in this plugin's memory. They are dropped when Zotero MCP is disabled, updated or reloaded, so register again whenever `Zotero.ZoteroMCP.api` becomes available.
- ---
- ## 🤝 Contributing
- Contributions are welcome! Please feel free to submit pull requests, report issues, or suggest enhancements.
- 1. Fork the repository.
- 2. Create your feature branch (`git checkout -b feature/AmazingFeature`).
- 3. Commit your changes (`git commit -m 'Add some AmazingFeature'`).
- 4. Push to the branch (`git push origin feature/AmazingFeature`).
- 5. Open a Pull Request.
- ## 📄 License
- This project is licensed under the [MIT License](./LICENSE).
- ## 🙏 Acknowledgements
- - [Zotero](https://www.zotero.org/) - An excellent open-source reference management tool.
- - [Model Context Protocol](https://modelcontextprotocol.org/) - The protocol for AI tool integration.
- - [](https://github.com/windingwind/zotero-plugin-template)
- Contact us
- 
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.