mcpField
Z
Zotero MCP

Zotero MCP

Local
github.com/BirdInTheTreeProductivity2Updated 32w ago

About Zotero MCP

Zotero MCP is a read-and-write MCP server for managing Zotero libraries from compatible AI clients. It combines literature search and metadata access with collection editing, BibTeX import, and duplicate merging.

Key features

  1. 01Search items with filters
  2. 02Read metadata and export BibTeX
  3. 03Create and update library items
  4. 04Manage collections and tags
  5. 05Import BibTeX entries
  6. 06Find and merge duplicates

Use cases

  1. 01Search papers by collection, type, or tag
  2. 02Add a DOI record to a library
  3. 03Import BibTeX into a collection
  4. 04Find and merge duplicate records

MCP support

Exposes Zotero search, reading, writing, collection, and duplicate-management operations as tools for MCP clients. Uses the Zotero Web API and requires an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

zotero-mcp

Read+write MCP server for Zotero. An MCP server with full write support for managing Zotero library from AI assistants.

It lets you create items, manage collections, find and merge duplicates, and import BibTeX from within Claude Code/Desktop, or any MCP-compatible client.

Uses the Zotero Web API (requires API key). Get the key at https://www.zotero.org/settings/keys.

Features

Search & Read
ToolDescription
search_itemsFull-text search with collection, type, and tag filters
get_itemDetailed metadata or BibTeX export for a single item
get_collectionsList all collections with hierarchy and item counts
get_collection_itemsList items in a specific collection
find_duplicatesFind duplicates by title/DOI, or scan entire library
get_tagsList all tags with item counts
Write
ToolDescription
create_itemCreate item from field data
create_item_from_doiCreate item by DOI (auto-fills metadata via Zotero translator + CrossRef)
import_bibtexImport BibTeX entries into a collection
update_itemUpdate item fields with version conflict protection
Collections
ToolDescription
create_collectionCreate a collection (with optional parent)
add_to_collectionsAdd an item to multiple collections at once
remove_from_collectionRemove item from collection (doesn't delete it)
Management
ToolDescription
merge_duplicatesMerge duplicates: transfer metadata, tags, collections to keeper, delete rest
delete_itemDelete an item

Installation

Requires Python 3.11+ and uv.

# Clone the repo
git clone https://github.com/BirdInTheTree/zotero-mcp.git
cd zotero-mcp
uv sync

Usage

Claude Code
claude mcp add zotero \
  -e ZOTERO_API_KEY=your-key \
  -e ZOTERO_USER_ID=your-user-id \
  -- uv run --directory /path/to/zotero-mcp python -m zotero_mcp
Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "zotero": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/zotero-mcp", "python", "-m", "zotero_mcp"],
      "env": {
        "ZOTERO_API_KEY": "your-key",
        "ZOTERO_USER_ID": "your-user-id"
      }
    }
  }
}

Configuration

VariableRequiredDescription
ZOTERO_API_KEYyesZotero Web API key
ZOTERO_USER_IDyesYour Zotero user ID

Get your API key at https://www.zotero.org/settings/keys. Your user ID is shown on the same page.

Examples

Once connected, you can ask your AI assistant things like:

  • "Search my Zotero for papers ..."
  • "Create a new collection called ..."
  • "Import this BibTeX into my collection"
  • "Find duplicate items in my library and merge them"
  • "Add this paper to both collections"
  • "Look up DOI 10.1234/example and add it to my library"

Development

# Install with dev dependencies
uv sync --dev

# Run tests
uv run pytest tests/ -v

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.