Compatible with every major AI agent and IDE
What is the Zotero MCP Server?
Connect your Zotero library to any AI agent and take full control of your research workflow through natural conversation.
What you can do
- Collections & Organization — List top-level collections, subcollections, and specific collection details to navigate your library structure.
- Item Management — Query all items, including notes and attachments, with support for advanced filtering by type, tag, or keyword.
- Metadata Inspection — Fetch complete bibliographic data, creator information, and publication details for any specific item.
- Tags & Publications — Access your personal publications and manage tags to categorize your research effectively.
- Group Libraries — Seamlessly switch between your personal library and shared group libraries using specific IDs.
How it works
- Subscribe to this server
- Enter your Zotero API Key and User ID
- Start managing your references from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Researchers & Academics — quickly find citations and organize papers without leaving your writing environment.
- Students — manage reading lists and extract metadata for bibliographies through simple chat.
- Knowledge Workers — centralize your document management and reference tracking within your AI-powered workspace.
Built-in capabilities (23)
Use get_new_item_template first to get the correct schema. Create new items in the Zotero library
Delete a single item
Delete multiple items (up to 50)
Get a specific collection by key
Get deleted objects since a specific library version
Get a specific item by key
List valid fields for a specific item type
Get a JSON template for creating a new item of a specific type
Get tags matching a specific name
List items in a specific collection
List all collections in the Zotero library
List child items (notes, attachments) for a specific item
List all available Zotero item fields
List tags for a specific item
List all available Zotero item types
List items in the Zotero library
List items in My Publications
List subcollections of a specific collection
List all tags in the library
List top-level collections in the Zotero library
List top-level items in the Zotero library
List items in the trash
Update an existing item (Partial Update / PATCH)
Why Google ADK?
Google ADK natively supports Zotero as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 23 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.
- —
Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution
- —
Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Zotero
- —
Production-ready features like session management, evaluation, and deployment come built-in. not bolted on
- —
Seamless integration with Google Cloud services means you can combine Zotero tools with BigQuery, Vertex AI, and Cloud Functions
Zotero in Google ADK
Zotero and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Zotero to Google ADK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Zotero in Google ADK
The Zotero MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 23 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Google ADK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Zotero for Google ADK
Every tool call from Google ADK to the Zotero MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search for specific items in my library using keywords?
Yes! Use the list_items tool with the q parameter. It performs a quick search across titles and creators to find exactly what you need.
How do I view the subcollections nested inside a main collection?
Simply use the list_subcollections tool and provide the collection_key of the parent collection. The agent will return all nested folders.
Does this support shared group libraries or only my personal library?
It supports both! Most tools, like list_collections or list_items, accept an optional group_id. If provided, the agent will query that specific group library instead of your personal one.
How does Google ADK connect to MCP servers?
Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.
Can ADK agents use multiple MCP servers?
Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.
Which Gemini models work best with MCP tools?
Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.
McpToolset not found
Update: pip install --upgrade google-adk
Explore More MCP Servers
View all →
Lacework (Cloud Security & CNAPP)
10 toolsSecure your cloud via Lacework — search security alerts, monitor vulnerabilities, and audit cloud asset inventory.

Cosmic
10 toolsManage headless content via Cosmic — list and create objects, audit schema types, handle media assets, and manage buckets directly from any AI agent.

Open-Meteo Climate & Ensemble
3 toolsProject the future of our planet: IPCC climate simulations to 2100, multi-model ensemble forecasts, and long-term temperature trends — the data backbone for ESG and climate policy AI.

OpenAI
10 toolsUse GPT-4o, DALL-E 3, embeddings, fine-tuning, and moderation as tools inside your AI agent workflows.
