# AI use cases for Scientific Figure Library (xuzhougeng/ScientificFigureLibrary)

Repo: [xuzhougeng/ScientificFigureLibrary](https://github.com/xuzhougeng/ScientificFigureLibrary) | Use cases: 3 | Page: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/

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.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Keep a versioned library of your figure templates: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/build-personal-figure-template-library/
- Reuse an exact figure template in a new project: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/reuse-exact-figure-in-new-project/
- Add the figure library to DeepSeek Harness: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/install-figure-library-in-dsh/

## How to keep a versioned library of your figure templates with Scientific Figure Library

Repo: [xuzhougeng/ScientificFigureLibrary](https://github.com/xuzhougeng/ScientificFigureLibrary) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

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

**Who it is for:** A researcher or bioinformatician who reuses plotting code across papers and wants every figure template versioned with the exact code that made it.

**The problem:** Figure scripts are scattered across old projects, and nobody remembers which version produced the plot in the published paper.

**The outcome:** One local library of reviewed figure templates, each release hashed and versioned, searchable from Claude, Codex, Cursor, Pi or dsh.

### Steps

1. For Pi run `pi install npm:pi-mcp-adapter` and then `pi install npm:scientific-figure-library`
2. For other stdio hosts, follow docs/QUICKSTART.md and register the server figure-library pointing at dist/index.js (Node.js 22 or newer)
3. Restart the host and call figure_library_get_skill, then figure_library_source_status
4. If it reports setup_required, bind one absolute global Library directory and a Local workspace
5. Import a figure image with its code and review it at the gate
6. Publish an immutable Release so it shows up under Local Published

### Prompt to paste into your agent

```text
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.
```

### Caveat

The server does not run plotting code; your host agent inspects and runs files.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/build-personal-figure-template-library/

## How to reuse an exact figure template in a new project with Scientific Figure Library

Repo: [xuzhougeng/ScientificFigureLibrary](https://github.com/xuzhougeng/ScientificFigureLibrary) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

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.

**Who it is for:** A researcher starting a new analysis who wants the same plot style and code as a past paper, not a redrawn approximation.

**The problem:** Asking an agent to recreate a figure gives a similar plot with different code, so styles drift between papers.

**The outcome:** The confirmed template's exact files copied into your project, ready to adapt to new data, with nothing copied until you approve it.

### Steps

1. Open the new project in your MCP host with the figure library installed
2. Ask the agent to open the workbench and search your Local Published templates
3. Preview candidates and confirm one card
4. Let the agent plan materialization into an empty folder you name
5. Approve the plan so the exact files are written
6. Swap in your new data inputs and run the code with your own R or Python setup

### Prompt to paste into your agent

```text
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.
```

### Caveat

Drawing new data still needs approved R or Python runtimes in your host.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/reuse-exact-figure-in-new-project/

## How to add the figure library to DeepSeek Harness with Scientific Figure Library

Repo: [xuzhougeng/ScientificFigureLibrary](https://github.com/xuzhougeng/ScientificFigureLibrary) | Difficulty: Beginner | Time: 10 minutes | Basis: From the README

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.

**Who it is for:** A DeepSeek Harness user doing scientific work who wants figure templates available inside dsh.

**The problem:** Adding an MCP server by hand to dsh is easy to get wrong, and a duplicate entry gives duplicated tools.

**The outcome:** The figure library registered once in your dsh profile, with the bundled figure skill and a bound library ready to search.

### Steps

1. Install the plugin: `dsh plugin --profile web add scientific-figure-library`
2. The profile flag is required; use web unless you run another profile
3. Restart the profile with `dsh --profile web` or `dsh web`
4. Run figure_library_get_skill, then figure_library_source_status
5. If setup_required appears, bind the global Library and Local workspace
6. Do not clone the repo or add a second figure-library MCP row, which duplicates tools

### Prompt to paste into your agent

```text
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.
```

### Caveat

The README says not to clone the repo or add a second figure-library MCP entry.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/xuzhougeng-scientificfigurelibrary/install-figure-library-in-dsh/