DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Scientific Figure Library: what you can do with it

What is Scientific Figure Library? Scientific Figure Library is a local-first MCP server and MCP App that lets you import, review and publish scientific figure templates with their code to one global library on disk and reuse exact versions across agent hosts.

How do I use it? For Pi run pi install npm:pi-mcp-adapter and then pi install npm:scientific-figure-library; then For other stdio hosts, follow docs/QUICKSTART.md and register the server figure-library pointing at dist/index.js (Node.js 22 or newer); Restart the host and call figure_library_get_skill, then figure_library_source_status. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Keep a versioned library of your figure templates

    Install Scientific Figure Library as an MCP server, bind one global Library folder, and import figures with their code as reviewed, immutable releases.

    View prompt
    Call figure_library_source_status. If writes are disabled, help me bind <absolute path> as my global Library after I confirm. Then import the figure <image path> with its code <script path>, review it and publish a release named <name>. Do not execute R or Python.

  • Reuse an exact figure template in a new project

    Search your Local Published library from your agent, confirm one template card, then materialize that exact version into an empty folder of the new project.

    View prompt
    Open the figure library workbench and search my Local Published templates for <plot type>. Wait for me to confirm one card. Then plan materialization into <empty folder>. Do not execute R or Python. Do not redraw the figure.

  • Add the figure library to DeepSeek Harness

    Install Scientific Figure Library as a dsh plugin on your web profile, restart it and run the first checks so the figure tools are ready.

    View prompt
    Install Scientific Figure Library for DeepSeek Harness. Run: dsh plugin --profile web add scientific-figure-library. Restart the web profile, then run figure_library_get_skill and figure_library_source_status, and tell me if I need to bind a Library.

Quick start with Scientific Figure Library

  1. Check you have what it needs: An MCP host such as Pi, DeepSeek Harness (dsh), Claude, Codex or Cursor; Node/npm for the Pi install.
  2. Open xuzhougeng/ScientificFigureLibrary on GitHub and read the README and license.
  3. For Pi run pi install npm:pi-mcp-adapter and then pi install npm:scientific-figure-library
  4. For other stdio hosts, follow docs/QUICKSTART.md and register the server figure-library pointing at dist/index.js (Node.js 22 or newer)
  5. Restart the host and call figure_library_get_skill, then figure_library_source_status
  6. If it reports setup_required, bind one absolute global Library directory and a Local workspace

These steps come from our top use case, Keep a versioned library of your figure templates, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for xuzhougeng/ScientificFigureLibrary

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Scientific Figure Library alternatives · Best AI repos for Research

About this repo

Requirements

  • An MCP host such as Pi, DeepSeek Harness (dsh), Claude, Codex or Cursor
  • Node/npm for the Pi install

Add this badge to your README

Maintain Scientific Figure Library? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/xuzhougeng/ScientificFigureLibrary.svg)](https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/?utm_source=github&utm_medium=badge&utm_campaign=xuzhougeng-ScientificFigureLibrary)

HTML 

<a href="https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=xuzhougeng-ScientificFigureLibrary"><img src="https://dedupedai.com/badge/xuzhougeng/ScientificFigureLibrary.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Scientific Figure Library

What is Scientific Figure Library?

Scientific Figure Library is a local-first MCP server and MCP App that lets you import, review and publish scientific figure templates with their code to one global library on disk and reuse exact versions across agent hosts. It is an open-source project on GitHub: https://github.com/xuzhougeng/ScientificFigureLibrary.

How do I use Scientific Figure Library?

For Pi run pi install npm:pi-mcp-adapter and then pi install npm:scientific-figure-library; then For other stdio hosts, follow docs/QUICKSTART.md and register the server figure-library pointing at dist/index.js (Node.js 22 or newer); Restart the host and call figure_library_get_skill, then figure_library_source_status. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Scientific Figure Library for?

Researchers who make figures with code and want reusable, versioned templates across projects and AI agents.

What can I do with Scientific Figure Library?

3 use cases so far, for example: Keep a versioned library of your figure templates; Reuse an exact figure template in a new project; Add the figure library to DeepSeek Harness. Each has steps and a copy-paste agent prompt.

What do I need to run Scientific Figure Library?

An MCP host such as Pi, DeepSeek Harness (dsh), Claude, Codex or Cursor; Node/npm for the Pi install.

What are alternatives to Scientific Figure Library?

Other hot AI repos in Research: Scientific Agent Skills, PersonaPlex, PageIndex, Book to Skill, Last30days Skill.

Is Scientific Figure Library safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.