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.
curl -O https://raw.githubusercontent.com/u9401066/academic-figures-mcp/main/.github/agents/research.agent.mdgit clone --depth 1 https://github.com/u9401066/academic-figures-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/agents/u9401066/academic-figures-mcp/research)<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.
<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>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 | $0.00034 | $0.01683 |
| Opus 5 | $0.00017 | $0.00842 |
| Sonnet 5 | $0.00007 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00168 |
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.
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」
generate_search_queries(topic)→ 取得 MeSH 詞彙和同義詞- 從結果中選擇最佳策略
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...」
parse_pico(description)→ 解析 P/I/C/O- 對每個元素呼叫
generate_search_queries() - 組合 Boolean 查詢: (P) AND (I) AND (C) AND (O)
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
- 匯入前必須詢問用戶要存入哪個 Collection
- 用
list_collections列出可用 Collection - 用
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 PMIDsget_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
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.
- 8d ago First seen · 178 lines · 34 tokens per session scan A 1bca4dd6de08
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.