Skip to main content
Glama
Sign In
zotero-comfort

zotero-comfort

by BIH-CEI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Zotero Comfort

High-level Zotero MCP integration with smart research workflows.

Overview

Zotero Comfort provides two layers of functionality:

A) Proxy Layer - Direct re-exposure of 54yyyu/zotero-mcp tools with a clean Python API.

B) Smart Workflows - High-level orchestrations for common research tasks.

Related MCP server: Zotero Agent

Installation

pip install zotero-comfort

Or with Docker:

docker build -t zotero-comfort .
docker run -e ZOTERO_API_KEY=xxx -e ZOTERO_LIBRARY_ID=123 zotero-comfort

Configuration

Set environment variables:

export ZOTERO_API_KEY="your-api-key"
export ZOTERO_LIBRARY_ID="your-library-id"
export ZOTERO_LIBRARY_TYPE="group"  # or "user"

Usage

As Python Library

from zotero_comfort import ZoteroProxy, ZoteroWorkflows

# Proxy layer - direct tool access
proxy = ZoteroProxy()
papers = proxy.search_papers("FHIR interoperability", limit=20)
metadata = proxy.get_metadata("ABC12345")

# Smart workflows - high-level operations
workflows = ZoteroWorkflows()
reading_list = workflows.build_reading_list("clinical NLP", max_papers=15)
result = workflows.smart_add_paper("10.1234/example.2024")
bibtex = workflows.export_bibliography(collection_name="FHIR")

As MCP Server

Add to your Claude configuration:

{
  "mcpServers": {
    "zotero-comfort": {
      "command": "zotero-comfort",
      "env": {
        "ZOTERO_API_KEY": "your-key",
        "ZOTERO_LIBRARY_ID": "your-library-id"
      }
    }
  }
}

Available Tools

Proxy Layer (A)

Tool

Description

zotero_search

Search papers by keyword

zotero_get_metadata

Get paper details

zotero_list_collections

List all collections

zotero_get_collection_items

Get items in collection

zotero_get_fulltext

Get paper full text

zotero_semantic_search

AI-powered semantic search

Smart Workflows (B)

Tool

Description

build_reading_list

Create curated topic reading list

smart_add_paper

Add paper with duplicate check

export_bibliography

Export as BibTeX

find_related_papers

Find semantically similar papers

Development

# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Lint
ruff check src/

License

MIT

Available Tools

17 tools
build_reading_listC

Build a curated reading list for a research topic

Inputs: topic (required), min_year, max_papers.

export_bibliographyC

Export papers as BibTeX bibliography

Inputs: tag, collection_name.

find_related_papersB

Find papers related to a given paper using semantic search

Inputs: item_key (required), limit.

get_library_statusA

Get status of configured libraries (group and personal)

Inputs: no named parameters.

search_arxiv_to_collectionB

Search arXiv and add results to a Zotero collection

Inputs: query (required), collection_name (required), max_results, create_collection.

search_group_libraryA

Search for papers in the group (shared team) library

Inputs: query (required), limit.

search_multi_source_to_collectionC

Search multiple sources (PubMed, arXiv) and combine results in a Zotero collection

Inputs: query (required), collection_name (required), sources, create_collection, +1 more.

search_personal_libraryB

Search for papers in your personal library

Inputs: query (required), limit.

search_pubmed_to_collectionB

Search PubMed and add results to a Zotero collection

Inputs: query (required), collection_name (required), max_results, create_collection.

set_default_libraryB

Set the default library for operations

Inputs: library (required).

smart_add_paperA

Add paper from DOI with duplicate checking and optional collection/tag assignment. Without collection_name, this is a dedup/metadata probe; with collection_name, the paper is fetched from Crossref and written to Zotero, or (if already in library) attached to the target collection without creating a duplicate record.

Inputs: doi (required), tags, collection_name, check_duplicates.

zotero_get_collection_itemsB

Get all items in a specific collection

Inputs: collection_key (required).

zotero_get_fulltextC

Get full text content of a paper

Inputs: item_key (required).

zotero_get_metadataB

Get detailed metadata for a specific paper

Inputs: item_key (required).

zotero_list_collectionsA

List all collections in the Zotero library

Inputs: no named parameters.

zotero_searchB

Search for papers in Zotero library by keyword

Inputs: query (required), limit.

zotero_semantic_searchC

AI-powered semantic search for similar papers

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 17 tools

    Disambiguation2/5

    Multiple search tools overlap: zotero_search, search_personal_library, search_group_library, zotero_semantic_search, and find_related_papers have unclear boundaries. Also zotero_semantic_search and find_related_papers both appear to provide similar-paper semantic search.

    Naming Consistency3/5

    Most names are snake_case and verb_noun, but prefix usage is inconsistent: zotero_* is mixed with bare search_* and action-style names like build_reading_list, smart_add_paper, and export_bibliography. Some near-duplicate functions have very different naming (zotero_semantic_search vs find_related_papers).

    Tool Count4/5

    17 tools is slightly above the typical well-scoped range, but the domain (search, collection management, external import, bibliography export, library configuration) justifies most of the surface. The extra weight comes from some redundant search variants rather than truly unnecessary tools.

    Completeness3/5

    The server covers searching, metadata, fulltext, collection listing, external imports, and export, but lacks essential library management operations such as updating or deleting items, creating/deleting collections, and tag management. Common Zotero workflows still have noticeble gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • zotero-cli-cc

      Agents365-ai
      A
      license
      Not graded
      quality
      A
      maintenance
      MCP server that exposes 45 tools for Zotero reference management, enabling AI agents to read/write items, search, extract PDF text, and manage workspaces via the Zotero CLI.
      221
      AGPL 3.0

    • Zotero Agent

      psiQAQ
      A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that embeds into Zotero, enabling AI agents to search, manage, enrich metadata, import papers, and automate research workflows through 42 tools including PDF retrieval and annotation synthesis.
      9
      MIT