Borrowing it
Nothing to install: this file belongs to Robernetes/zotero-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Robernetes/zotero-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Robernetes/zotero-mcpWrote 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.
[](https://agentmods.dev/instructions/robernetes/zotero-mcp/agents-md)<a href="https://agentmods.dev/instructions/robernetes/zotero-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/robernetes/zotero-mcp/agents-md/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.
<a href="https://agentmods.dev/instructions/robernetes/zotero-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/robernetes/zotero-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02017 | $0.02017 |
| Opus 5.5 | $0.00807 | $0.00807 |
| Sonnet 5.5 | $0.00403 | $0.00403 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
zotero-mcp AGENTS.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zotero-mcp — instrucciones para agentes
Servidor MCP por stdio (Node ≥ 18, ESM, JavaScript sin compilar) para la biblioteca
local de Zotero, empaquetado como plugin de Antigravity (plugin.json,
mcp_config.json, skills/). Lee de la API local de Zotero, guarda items nuevos a
través del conector de Zotero y edita documentos .md/.docx del usuario.
Uso, herramientas y configuración para el usuario: README.md.
Mapa del repositorio
src/server.js: entrada stdio.src/app.js:createServer(ctx)registra todas las herramientas (los tests lo usan en memoria).src/context.js: variables de entorno →configy clientes compartidos (ToolContext).src/tools/: registro de herramientas por área (library,citations= Markdown,word=.docx,external);shared.jstieneok/fail/run.src/zotero-client.js(API local, lectura),src/zotero-connector.js(conector, guardar),src/external-search.js(OpenAlex/Crossref).src/cite.js(citeproc y registro de citas en memoria),src/bib-section.js(sección de referencias en Markdown),src/docx.js(OOXML y camposZOTERO_ITEM/ZOTERO_BIBL),src/file-io.js(escritura segura),src/workspace.js(carpetas permitidas).src/csl/,src/locales/: estilos y locales CSL de terceros (CC-BY-SA 3.0); no editarlos a mano.skills/zotero-research/SKILL.md: instrucciones para el agente que usa el MCP.estructura-skills-mcp-plugins-antigravity.md: guía genérica de plugins de Antigravity con ejemplos ficticios (SQL, SAP); no describe este proyecto.
Límites de arquitectura
- Solo
src/server.js,src/app.jsysrc/tools/importan@modelcontextprotocol/sdkozod. Los clientes y la lógica de documentos no dependen de MCP. - Las herramientas reciben sus dependencias por
ctx; no crean clientes ni leenprocess.env. Una variable nueva se lee enloadConfigconenvValue(que ignora${VAR}sin expandir) y se añade a.env.example,mcp_config.jsony la tabla de configuración de ambos README. - Los handlers envuelven la lógica en
run(...)y responden conok(payload)/fail(mensaje); los errores son mensajes en español que dicen qué hacer. - stdout es el canal JSON-RPC: nada de
console.logensrc/; diagnóstico solo conconsole.error. - Toda ruta de documento pasa por
workspace.resolve(filePath, { extensions })antes de leerla. - Toda escritura de documento va dentro de
withFileLock, lee conreadFileForEdit/openDocxy escribe conwriteFileAtomic/saveDocx(huella mtime/tamaño,.bak, renombrado atómico). Nuncafs.writeFiledirecto sobre un documento. - Las herramientas que escriben solo lo hacen con
apply: true; sin él devuelven vista previa. - Biblioteca de Zotero: solo lectura por la API local; la única escritura es
zotero_add_item(conector,apply: true). No añadir operaciones que editen o borren items. src/docx.jsparsea conpreserveOrdery sin procesar entidades para que abrir → guardar reproduzca el documento: decodificar condecodeXmlal leer y codificar conencodeXmlal crear nodos. No cambiarXML_OPTSsin pruebas de ida y vuelta entests/docx.test.js.- Las citas
.docxsiguen el formato del plugin de Word (URI del item,citationIDaleatorio,noteIndex0) yensureDocumentPrefsnunca pisa preferencias existentes. - Estilos y locales:
AVAILABLE_STYLESyLOCALESensrc/cite.jsse leen desrc/csl/<nombre>.cslysrc/locales/locales-<código>.xmlal arrancar; no hay listas fijas que mantener. - La versión sale solo de
package.json(src/version.js).
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.
- yesterday First seen · 90 lines · 2,017 tokens per session scan A b8fb2d6abc85
zotero-mcp AGENTS.md is an instructions file published in the GitHub repository Robernetes/zotero-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 2,017 tokens to every session, about $0.0081 per session on Opus 5.5. 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 2026-11-05.
zotero-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zotero-mcp AGENTS.mdRobernetes/zotero-mcp | Instructions file | 1 | yesterday | MIT | A | 2,017 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |