Zotero CLI

What it does

When your agent uses it

• Finding papers in a Zotero library by title, author or topic
• Reading the full text or page ranges of a saved PDF
• Adding items to the library by DOI, URL or ISBN
• Exporting a bibliography from selected items

Example prompts

• “Search my Zotero library for papers about diffusion models and summarize the top five.”
• “Add the Attention Is All You Need paper to my transformers collection and tag it important.”
• “Export a BibTeX bibliography of everything I tagged to-read.”
• “What did I write in my notes about the research question for the survey paper?”

Requirements

• The `zotero-cli` command
• Zotero desktop app with its local API enabled, or ZOTERO_API_KEY and ZOTERO_LIBRARY_ID for web mode
• A built search index for semantic search

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1zotero-cli --json layout ATTACHMENT_KEY lists figure, table and
2. 2Write one JSON object per line: `{"page": 4, "text": "exact words",
3. 3zotero-cli annotations batch --attachment-key ATTACHMENT_KEY --file plan.jsonl --dry-run
4. 4Run it again without --dry-run. Anything that did not land is listed

What it can do on your machine

Read from SKILL.md and the folder at commit 0faf1b2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ATTACHMENT_KEY
  • ITEM_KEY
  • ZOTERO_API_KEY
  • ANNOTATION_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Zotero CLI loads about 2.3k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 1,023 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~103

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from 54yyyu/zotero-mcp at commit 0faf1b2, republished under its MIT licence (© 54yyyu). 1,023 words, ~2,271 tokens.

name

zotero-cli

description

Read and write a Zotero library from the shell with the `zotero-cli` command - search papers by keyword or meaning, read PDF full text and page ranges, get and set metadata, manage collections, tags, notes and annotations, add items by DOI/URL/ISBN, and export bibliographies. Use whenever the user asks about their Zotero library, references, citations, papers they have saved, or their reading notes.

zotero-cli config          # prints the resolved Zotero settings

{"ok": true, "command": "search", "schema": 1, "data": {...}}
{"ok": false, "command": "search", "schema": 1, "error": {"message": "...", "code": "..."}}

# 1. find - use --detail keys_only to keep the result small while browsing
zotero-cli --json search "attention mechanisms" --limit 10 --detail keys_only

# 2. act - metadata, full text, or a page range
zotero-cli --json get metadata ABCD1234
zotero-cli --json get fulltext ABCD1234
zotero-cli --json read ABCD1234 --start-page 3 --end-page 8

zotero-cli --json search "diffusion models" --limit 5 --detail keys_only \
  | jq -r '.data.items[].key' \
  | while read -r key; do zotero-cli --json get metadata "$key"; done

zotero-cli search "Cladder-Micus" --all-libraries

zotero-cli --json outline ABCD1234
zotero-cli --json read ABCD1234 --find "robustness check"
zotero-cli --json read ABCD1234 --start-page 42 --end-page 55

zotero-cli --json get collection-items QS7TQPPA --limit 100 --offset 100

zotero-cli add doi 10.1038/s41586-021-03819-2 -c "Reading List"
zotero-cli edit ABCD1234 --title "Corrected Title" --add-tags reviewed
zotero-cli notes create --item-key ABCD1234 --text "Key finding: ..."
zotero-cli batch --item-keys A1B2C3D4,E5F6G7H8 --add-tags screened

zotero-cli get children ITEM_KEY                          # the PDF's attachment key
zotero-cli read ITEM_KEY --start-page 1 --end-page 99     # end page clamps to the last page
zotero-cli path ATTACHMENT_KEY                            # the PDF file on disk
zotero-cli open ITEM_KEY --page 7                         # show that page in the Zotero reader
zotero-cli open --annotation ANNOTATION_KEY               # jump to one annotation and select it

zotero-cli read ITEM_KEY --start-page 4 --format image                         # PNG per page, up to 10
zotero-cli read ITEM_KEY --start-page 4 --format image --rect 0.35,0.49,0.3,0.05   # zoom into one region

© 54yyyu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in src/zotero_mcp/skills/zotero-cli of 54yyyu/zotero-mcp.

• SKILL.md
• reference.md

Open the folder on GitHubat commit 0faf1b2