xuzhougeng/ScientificFigureLibrary
Scientific Figure Library (SFL) is a local-first MCP server and MCP App for your scientific figures. You import a figure and its code, review them, publish an immutable Release to one global Library on your machine, then reuse that exact template across projects in Claude Science, Wisp Science,
catalog descriptioncatalog 简介 / catalog description:Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.
Project Overview项目介绍
Scientific Figure Library (SFL) is a local-first MCP server that works with any stdio MCP host, including DSH, Claude Science, Wisp Science, Codex, Cursor, and Pi. It lets users import their own figures and corresponding plotting code, review the entries, then publish immutable releases to a single global library stored on the user’s local machine. To install SFL for DSH, users run dsh plugin --profile web add scientific-figure-library then restart the web profile, and should not add a duplicate local MCP entry if they already have one set up correctly.
SFL is designed for researchers and developers who regularly reuse scientific figure templates across multiple coding projects. It does not execute plotting code itself—all file inspection and code execution is handled by the host AI agent, and SFL only manages hashing, versioning, and access control for stored templates. The default retrieval order prioritizes locally published templates first, followed by FigureYa and Open Figure Modules, and users can enable additional custom personal providers. After installation, users must bind a global library directory on their local disk, and if setup is required, bind a local workspace before they can run their first search for templates.
SFL is released under the MIT license for its own code, and requires Node.js 22 or newer to run unless you use one of the pre-bundled official releases that include a compatible Node build. Pre-built native releases are available for macOS (Apple Silicon and Intel), Windows, and Linux, with both bundled-Node and no-node editions available for direct download from the project’s releases page. The bundled community snapshot is frozen and excluded from default search, and first-time users need to test the skill retrieval and source status commands before starting to use the library regularly.
科学图表库(Scientific Figure Library,简称SFL)是一个本地优先的MCP服务器,支持包括DeepSeek Harness(DSH)、Claude Science、Wisp Science、Codex、Cursor、Pi在内的多个符合MCP标准的AI代理。用户可以导入自制图表和对应代码,审核后发布为不可变版本,存储在本地机器的全局库中,方便跨项目复用相同模板。SFL本身不执行绘图代码,仅负责哈希计算、版本管理和发布管理,具体文件读取由宿主AI代理完成。
这个工具面向科研工作者和需要复用科学图表模板的开发人员,典型工作流是安装完成后先绑定本地全局库目录,如果提示需要设置,再绑定本地工作区,之后搜索匹配需求的图表模板,确认版本后再将选中的模板实例化到当前项目。默认检索顺序为本地已发布模板 → FigureYa → 开放图模块,用户也可以添加启用自定义个人数据源。
SFL采用MIT许可证,需要Node.js 22或更高版本才能运行,提供了带Node.js打包的macOS、Windows、Linux版本,也提供无Node的版本供已有环境的用户使用。官方捆绑的社区快照默认不加入搜索,绑定后首次使用需要先测试技能获取和源状态检查,按提示完成配置后即可正常使用。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:ScientificFigureLibrary(xuzhougeng/ScientificFigureLibrary)
仓库:https://github.com/xuzhougeng/ScientificFigureLibrary
本站详情页:https://www.yhbd.top/plugins/xuzhougeng-scientificfigurelibrary/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 100 · 最近提交 2026-10-03 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- This site's static screen found no obvious risk signal (stars, license, activity, manifest)本站静态筛查没发现明显风险信号(星标、许可证、更新活跃度、清单完整度)
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add scientific-figure-library
把 xuzhougeng/ScientificFigureLibrary 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
Scientific Figure Library
Website · 简体中文 · Quickstart · User Guide (online) · Protocol · Releases · Wisp Science
Scientific Figure Library (SFL) is a local-first MCP server and MCP App for your scientific figures. You import a figure and its code, review them, publish an immutable Release to one global Library on your machine, then reuse that exact template across projects in Claude Science, Wisp Science, Codex, Cursor, Pi, dsh, and other stdio MCP hosts.
The Library stays on disk you choose. Nothing is copied into every project until you confirm a materialization. The server does not execute plotting code and does not contain a second model: the host agent inspects files; SFL hashes, versions, gates, and publishes them.
The default retrieval order is Local Published → FigureYa → Open Figure
Modules → enabled dynamic personal Providers. The bundled Community snapshot
is retained for explicit compatibility, but is frozen and excluded from default
search (includeInDefaultSearch: false). The source of truth for your own
figures is always Local Published.
A bundled extra catalog may currently contain zero releases after an authorized redaction; that is a healthy empty source, not a failure, and default search continues across other providers.
Search your local published library in the MCP App, confirm one exact template, then materialize it into a project.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
titanwings/distilly
YuJunZhiXue/dsh-purge
Clearailhc/clearai-dsh
yejiming/MuseAI
superdesigndev/superdesign-skill
Miaotofu01/Study-Mate