Paper Banana vs Pyscn

Two MCP servers from our science & health ranking, compared on live data - updated nightly, never sponsored.

Bottom line · 2026-09-30

Paper Banana records significantly more monthly package installs (13,171 vs 2,409); both are actively maintained, with commits inside the last month.

How they differ in kind

Paper Banana focuses on: Automated Academic Illustration for AI Scientists An agentic framework for generating publication-quality academic diagrams and statistical plots from text descriptions. Pyscn focuses on: Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score. Environment-variable extraction: Paper Banana yielded 12 variables; Pyscn yielded 1 variable. Implementation languages differ (Python vs Go).

What each one does

Paper Banana

Automated Academic Illustration for AI Scientists An agentic framework for generating publication-quality academic diagrams and statistical plots from text descriptions. Supports OpenAI (GPT-5.2 + GPT-Image-1.5), Azure OpenAI / Foundry, Google Gemini, and Atlas Cloud providers. It runs locally over stdio via the published package.

From the project's README.

Pyscn

Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score. It runs locally over stdio via the published package.

From the project's README.

14 signals, side by side

Signal Paper Banana Pyscn
Monthly installs 13,171 2,409
GitHub stars 2,387 1,085
Last commit 2026-09-17 2026-09-28
Releases · last 90 days 0 10+
In the registry since Feb 2026 Jul 2026
Registry versions 1 11
Documented tools not extracted - see README not extracted - see README
Env vars extracted 12 1
Runs local (stdio) local (stdio)
Endpoint auth local only local only
Maintenance actively maintained actively maintained
License MIT MIT
Language Python Go
Category rank #2 of 75 #3 of 75

Environment variables found in the READMEs

These are extracted names, not a requiredness check. Project docs may mark them optional or require other setup.

Paper Banana

  • GOOGLE_API_KEY
  • OPENAI_API_KEY
  • OPENAI_BASE_URL
  • OPENAI_VLM_MODEL
  • OPENAI_IMAGE_MODEL
  • ATLASCLOUD_API_KEY
  • ATLASCLOUD_BASE_URL
  • ATLASCLOUD_VLM_MODEL
  • ATLASCLOUD_IMAGE_BASE_URL
  • ATLASCLOUD_IMAGE_MODEL
  • GOOGLE_VLM_MODEL
  • GOOGLE_IMAGE_MODEL

Pyscn

  • PYSCN_CONFIG

Which one, for what

Derived from the signals above, not hands-on testing.

Pick Paper Banana if…

  • → you want the more widely installed option - 13,171 monthly installs vs 2,409
  • → you prefer a Python codebase to extend or audit

Pick Pyscn if…

  • → release velocity matters - 10+ releases in 90 days vs 0
  • → you prefer a Go codebase to extend or audit

Who's behind them

Paper Banana - llmsresearch: 1 MCP server tracked, 1 maintained, 2,387 combined stars.

Pyscn - ludo-technologies: 1 MCP server tracked, 1 maintained, 1,085 combined stars.

Not sold on either?

The next-ranked science & health servers we track:

Quick answers

Is Paper Banana better than Pyscn?

Package installs favor Paper Banana: 13,171 monthly installs to 2,409. Pyscn still ranks #3 of 75 maintained science & health servers. Data as of 2026-09-30; we haven't hands-on tested either.

Can I use Paper Banana and Pyscn together?

Yes - MCP clients accept multiple servers in one config, so you can enable both science & health servers side by side. If their tools overlap, keep the one whose toolset fits to keep your agent's tool list lean.

What environment variables do their READMEs document?

Paper Banana: 12 environment variables extracted from the README setup; Pyscn: 1 environment variable extracted from the README setup. Extraction does not rule out other authentication or configuration steps; check each project's current documentation.

Keep exploring: best science & health servers · Python servers · Go servers · all comparisons · every server

Methodology: package-usage signal = npm/PyPI installs (last month, platform APIs) · maintenance = commit recency + release cadence (GitHub) · tool lists and environment-variable names extracted from each project's README · endpoint auth from our own nightly probes. We haven't hand-tested these servers; everything here is data as of 2026-09-30.