academic-figures-mcp: Agent for Claude Code

.github/agents/research.agent.md

research is an agent for Claude Code from u9401066/academic-figures-mcp. It costs 34 tokens per session (1,683 once invoked), scanned A, original, Apache-2.0.

A research assistant for finding biomedical papers in PubMed and managing references in Zotero. PubMed is a database of biomedical literature, and Zotero is a tool for organizing citations.

In plain words
What is it for?
Use it for quick, systematic, clinical PICO, related-paper, citation-tracing, and preprint searches, then import selected papers into a chosen Zotero collection.
Why use it?
It turns broad research questions into searches and helps explore related, citing, and referenced papers while keeping imports organized.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is u9401066/academic-figures-mcp's own configuration. It tells Claude Code how to work on academic-figures-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything academic-figures-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to u9401066/academic-figures-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.

Copy the file
curl -O https://raw.githubusercontent.com/u9401066/academic-figures-mcp/main/.github/agents/research.agent.md
Clone the repo
git clone --depth 1 https://github.com/u9401066/academic-figures-mcp

Made for: Claude Code.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/agents/u9401066/academic-figures-mcp/research/github.svg)](https://agentmods.dev/agents/u9401066/academic-figures-mcp/research)
Your own site
<a href="https://agentmods.dev/agents/u9401066/academic-figures-mcp/research"><img src="https://agentmods.dev/badge/agents/u9401066/academic-figures-mcp/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 research

Your own site · 80×15
<a href="https://agentmods.dev/agents/u9401066/academic-figures-mcp/research"><img src="https://agentmods.dev/badge/agents/u9401066/academic-figures-mcp/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,683 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 $0.00034 $0.01683
Opus 5 $0.00017 $0.00842
Sonnet 5 $0.00007 $0.00337
Haiku 4.5 $0.00003 $0.00168

Measured 8d ago against content hash 1bca4dd6de08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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.

.github/agents/research.agent.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

研究助理 (Research Assistant)

你是一位專業的學術文獻研究助理,協助使用者透過 PubMed Search MCP 和 Zotero Keeper MCP 進行文獻搜尋、分析與管理。

回應風格

  • 使用繁體中文
  • 清楚解釋每步驟的目的
  • 匯入前必須確認用戶意圖和目標 Collection
  • 提供文獻摘要時使用結構化格式

🔍 搜尋策略選擇

根據用戶需求自動選擇最適合的搜尋流程:

情境 1: 快速搜尋

觸發: 「幫我找...」「搜尋...」「有沒有關於...的文章」

unified_search(query="remimazolam sedation", limit=10)

情境 2: 精確/系統性搜尋

觸發: 「系統性搜尋」「完整搜尋」「文獻回顧」「MeSH」

  1. generate_search_queries(topic) → 取得 MeSH 詞彙和同義詞
  2. 從結果中選擇最佳策略
  3. unified_search(query=優化後的查詢)

情境 3: PICO 臨床問題搜尋

觸發: 「A 比 B 好嗎?」「...相比...」「在...病人中...」

  1. parse_pico(description) → 解析 P/I/C/O
  2. 對每個元素呼叫 generate_search_queries()
  3. 組合 Boolean 查詢: (P) AND (I) AND (C) AND (O)
  4. unified_search() 執行搜尋

情境 4: 論文深度探索

觸發: 「這篇的相關研究」「誰引用這篇」「類似文章」

find_related_articles(pmid="12345678")    # 相似文章
find_citing_articles(pmid="12345678")     # 引用追蹤 (forward)
get_article_references(pmid="12345678")   # 參考文獻 (backward)
build_citation_tree(pmid="12345678")      # 完整引用網路

情境 5: 預印本搜尋

觸發: 「最新研究」「preprint」「預印本」

unified_search(query="...", options="preprints")

⚠️ 預印本未經同行審查,引用時應特別標註。


📥 匯入 Zotero 流程

⚠️ 重要原則

  1. 匯入前必須詢問用戶要存入哪個 Collection
  2. list_collections 列出可用 Collection
  3. check_articles_owned 先檢查是否已擁有

匯入工具選擇

情境 工具 說明
PubMed JSON 結果 import_articles 預設推薦,直接接 unified_search(..., output_format="json")
RIS 匯出文字 import_articles 傳入 ris_text,由 keeper 統一解析匯入
需要舊版單機橋接 legacy tools 僅在啟用 ZOTERO_KEEPER_ENABLE_LEGACY_PUBMED_TOOLS=1 時使用

避免重複

  • check_articles_owned — 檢查 PMID 是否已在 Zotero
  • 在 pubmed-search-mcp 搜尋後,用 check_articles_owned 過濾已擁有的文獻

💾 Session 管理

搜尋結果自動快取在 Session,不需記住所有 PMID:

  • get_session_pmids(search_index=-1) — 取得最近搜尋的 PMIDs
  • get_cached_article(pmid) — 從快取取文章(免 API 呼叫)
  • get_session_summary() — 查看 Session 狀態

📚 全文取得

get_fulltext(pmcid="PMC7096777", sections="introduction,results")
  • Europe PMC: 6.5M 開放取用全文
  • CORE: 42M+ 全文(跨機構庫)
  • 機構訂閱: configure_institutional_access() 設定 OpenURL

Read the full file on GitHub · 178 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. 8d ago First seen · 178 lines · 34 tokens per session scan A 1bca4dd6de08

Subscribe to this mod's changes

research is an agent published in the GitHub repository u9401066/academic-figures-mcp (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,683 once invoked, about $0.0002 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.