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.

<p align="center"><em>Search your local published library in the MCP App, confirm one exact template, then materialize it into a project.</em></p>

Local client preview

Separate native macOS Apple Silicon and Intel DMGs, plus Windows and Linux ZIPs with bundled Node, are available through the local-client release workflow. Both bundled-Node and no-node editions (requiring installed Node.js 22+) omit gallery images and download previews on demand. See installation and preview limitations. The macOS preview is ad-hoc signed and is not notarized.

Install with a coding agent

Node.js 22+ is required. Do not execute user plotting code. After install, bind one global Library directory on disk; if setup_required, also bind a Local workspace before searching.

Pi

Install the published npm package. Do not pi install a GitHub URL or git clone: the repository does not contain dist/, so MCP cannot start.

pi install npm:pi-mcp-adapter
pi install npm:scientific-figure-library

Restart Pi. The package loads the figure-library Skill and registers the stdio MCP server through pi-mcp-adapter. If you already copied a local SFL app MCP config into ~/.config/mcp/mcp.json or .mcp.json, skip pi install npm:scientific-figure-library — that duplicates tools.

Paste this request:

Install Scientific Figure Library for Pi.
Run: pi install npm:pi-mcp-adapter
Then: pi install npm:scientific-figure-library
Restart Pi. Do not clone the GitHub repo and do not add a second
figure-library MCP entry. First test: figure_library_get_skill, then
figure_library_source_status. If setup_required, bind the global Library
and Local workspace. Tell me when I need to restart Pi.

DeepSeek Harness (dsh)

--profile is required. Use web unless you run another profile.

…