zotero-research

zotero-research is a skill for Claude Code, Codex from Robernetes/zotero-mcp. It costs 72 tokens per session (1,215 once invoked), scanned A, original, MIT.

A workflow for searching a local Zotero library and adding properly formatted citations and bibliographies to Markdown or Word documents. Zotero is a reference manager that stores research sources; supported styles include APA, MLA, Chicago, Harvard, IEEE, and Vancouver.

In plain words
What is it for?
For finding references, viewing source details, inserting citations, and creating or updating bibliographies in Markdown and Word files.
Why use it?
It reduces manual searching, citation formatting, and bibliography updates when writing research-based documents. Zotero must be open and allow local application access.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit For finding references, viewing source details, inserting citations, and creating or updating bibliographies in Markdown and Word files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/robernetes/zotero-mcp/zotero-research
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Robernetes/zotero-mcp --skill zotero-research
Clone the repo
git clone --depth 1 https://github.com/Robernetes/zotero-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zotero-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/robernetes/zotero-mcp/zotero-research/github.svg)](https://agentmods.dev/skills/robernetes/zotero-mcp/zotero-research)
Your own site
<a href="https://agentmods.dev/skills/robernetes/zotero-mcp/zotero-research"><img src="https://agentmods.dev/badge/skills/robernetes/zotero-mcp/zotero-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for zotero-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/robernetes/zotero-mcp/zotero-research"><img src="https://agentmods.dev/badge/skills/robernetes/zotero-mcp/zotero-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01215
Opus 5 $0.00036 $0.00607
Sonnet 5 $0.00014 $0.00243
Haiku 4.5 $0.00007 $0.00121

Measured 11d ago against content hash 0c08501fb572, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zotero-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/zotero-research/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigación y citas con Zotero

Este flujo conecta con la biblioteca local de Zotero (API local en el puerto 23119). Zotero debe estar abierto con el ajuste "Allow other applications on this computer to communicate with Zotero" habilitado.

1. Buscar referencias

  1. Usa zotero_search con palabras clave (query).
  2. Si el usuario menciona una carpeta/colección, consúltala con zotero_list_collections y filtra con collectionKey.
  3. Presenta los resultados con: clave, título, autores y año. No inventes datos: usa solo lo que devuelve la herramienta.

2. Obtener detalles

Usa zotero_get_item con la key cuando necesites el detalle completo de un item.

3. Citar

  1. Determina el estilo del documento (APA, MLA, Chicago, Harvard, IEEE, Vancouver). Si es ambiguo, pregunta al usuario.
  2. Llama zotero_cite con:
    • key (de Zotero),
    • style (ej. apa),
    • locator y label cuando la cita apunte a una página concreta (ej. locator: "15", label: "page").
  3. Insertar la cita depende del formato del documento:
    • Markdown: la cita se inserta como texto en el flujo de edición.
    • Word (.docx): usa zotero_insert_citation_docx (ver sección 5).
  4. Usa siempre el mismo style y locale para todo el documento; cambiar de estilo a mitad de documento reinicia la numeración.

4. Mantener la bibliografía actualizada en Markdown

La bibliografía se actualiza sola al añadir citas:

  1. Añade todas las citas del documento con zotero_cite (se registran automáticamente).
  2. Llama zotero_bibliography con:
    • filePath = ruta del documento Markdown, y
    • apply: true para escribir el archivo.
  3. La sección de referencias se regenera a partir de las citas registradas. Si el documento aún no tiene sección, pasa createSection: true para crearla al final (por defecto ## Bibliografía).
  4. Para revisar sin escribir, omite apply (actúa en modo dryRun y devuelve el diff).

5. Trabajar con documentos Word (.docx)

Para insertar citas y bibliografía en archivos Word, usa las herramientas específicas de docx. No uses las herramientas de Markdown (zotero_cite textual, zotero_bibliography con filePath .md) en un .docx.

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 84 lines · 72 tokens per session scan A 0c08501fb572

Subscribe to this mod's changes

zotero-research is a skill published in the GitHub repository Robernetes/zotero-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,215 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories