Zotero Agent logo

Zotero Agent

Unclaimed

by psiQAQ

An AI agent framework for Zotero, enabling intelligent literature search, organization, annotation, and automated research workflows through MCP and JavaScript automation.

Install

$claude mcp add --transport http zotero-mcp http://127.0.0.1:23120/mcp `

Set up this server

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions
academic-researchbibliographyjavascriptliteratureliterature-managementmcpmodel-context-protocolresearchresearch-automationzotero

More in Search & Web

Browse the full directory

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

40 of 40 tools

Documented tools (40)

From project documentation. A server handshake does not verify each tool’s description or behavior.

add_items_to_collection

Add one or more items to a collection.

check_retractions

Check items against scite.ai editorial notices such as retractions or corrections.

create_collection

Create a new collection, optionally under a parent collection.

delete_collection

Delete a collection, with optional item deletion.

enrich_item_metadata

Fill missing fields (abstract/venue/volume/issue/pages/ISSN/publisher/date) from a DOI via doi.org CSL-JSON + OpenAlex; dry-run default, confirm write requires write.enabled.

extract_identifier_from_pdf

Mine DOI or arXiv ID from a PDF's fulltext cache using frequency voting. Read-only.

find_doi

Reverse-lookup a DOI via CrossRef title-similarity (≥0.86 threshold), or mode:"repair" to validate a dead DOI (Handle System API) and propose a replacement; dry-run default, confirm write requires write.enabled.

find_missing_pdfs

Report items without PDFs or fetch open-access PDFs for them.

find_similar

Find items that are semantically similar to a given item.

fulltext_database

Access the cached full-text database with list, search, get, and stats actions.

get_annotations

Get annotations and notes for a specific item or annotation ID.

get_collection_details

Get detailed information for a specific collection.

get_collection_items

List items inside a specific collection.

get_collections

List collections in the library, including recursive tree output when needed.

get_content

Read full-text content from PDFs, attachments, notes, and abstracts.

get_item_abstract

Get the abstract or summary of a specific item.

get_item_details

Get detailed metadata for a specific Zotero item.

get_libraries

List the Zotero libraries available in the current client.

get_subcollections

Get child collections under a specific collection.

import_bibliography

Bulk-import BibTeX / RIS / CSL-JSON (auto-detected); idempotent dedup by DOI / title similarity; dry-run plan by default.

import_by_identifier

Import an item by DOI, arXiv ID, ISBN, or PMID.

install_plugin_from_url

Install or upgrade a plugin XPI from a reachable URL or file path.

manage_pdf_resolvers

Register Sci-Hub / Anna's Archive into Zotero's native PDF resolver pref (grey sources default automatic=false, manual-only); actual download is via findmissingpdfs.

reload_plugin

Reload an installed Zotero plugin for development workflows.

remove_items_from_collection

Remove one or more items from a collection without deleting them from the library.

run_javascript

Execute JavaScript inside the Zotero process for advanced automation.

search_annotations

Search highlights, notes, and comments by query, color, tag, or item scope.

search_collections

Search collections by name.

search_fulltext

Search across cached full-text document content and return matching passages.

search_libraries

Search libraries by name.

search_library

Search the Zotero library with filters such as title, year, full text, item type, and relevance scoring.

search_web_of_science

Search Clarivate Web of Science Starter API with an advanced query; applies plan-aware rate, daily, and per-call safeguards and returns normalized records for identifier-based import.

semantic_search

Run embedding-based semantic search to find conceptually related content.

semantic_status

Show the status and index statistics of the semantic search service.

update_collection

Rename or move an existing collection.

upgrade_preprints

Find the published version of arXiv-style preprints via OpenAlex title search and upgrade DOI/venue/date/itemType; old values backed up into Extra; dry-run default.

write_item

Create items, re-parent attachments, or import local files as attachments.

write_metadata

Update item metadata such as title, abstract, DOI, date, or creators.

write_note

Create, update, or append Zotero notes.

write_tag

Add, remove, or replace tags on Zotero items.

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Zotero Agent MCP Server

How do I connect Zotero Agent MCP Server to Claude?
The listing records `claude mcp add --transport http zotero-mcp http://127.0.0.1:23120/mcp `` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code as compatible clients.
Is Zotero Agent MCP Server free?
The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Zotero Agent MCP Server do?
Zotero Agent MCP Server documents 40 tools to the agent, including add_items_to_collection, check_retractions, create_collection. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.