PaperBanana-CN: Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls

by mituan-ai · MCP Server · ★ 85

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Image Generation

How to install PaperBanana-CN

uvx paperbanana-cn studio
uv tool install paperbanana-cn

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 57/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 99 tools we ran end to end on the same task for our Image Generation page (2026-11-08).

Result: A pipeline for research-paper figures: 3 pictures in 20 minutes. · 3 of the 6 pictures in 20 minutes · 20.1 min · 3 image calls ($0.04)

What it made in our test

See the six pictures → · See the whole test →

academic-figuresbilingualgradioimage-generationmcppaperbananapythonscientific-visualization

Quick Facts

Stars85
Forks5
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score57/100
Open Issues10
Last Updated2026-10-01
Created2026-04-24
Platformsmcp, python
Est. Tokens~13k

About PaperBanana-CN

English · 简体中文 PaperBanana-CN generates methodology diagrams from research descriptions and statistical plots from CSV or JSON data. It uses the PaperBanana scientific workflow and adds separate VLM and image-service connections, a Chinese Studio interface, and explicit aspect-ratio and resolution controls. <img src="https://img.

Compatible Skills

These tools work well together with PaperBanana-CN for enhanced workflows:

  • AgentFigureGallery — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • FigMirror — semantic(0.22)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • Z-Image-Turbo-Windows — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)

PaperBanana-CN alternative? Top 6 similar tools

Looking for a PaperBanana-CN alternative? If you're comparing PaperBanana-CN with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • polish-sci-figures by zhoy0409-debug · ⭐ 81

    Scientific figure toolkit and Figure Studio: editable templates, local statistics, multi-panel editing and SVG

  • chibi by s-nagaev · ⭐ 56

    Your Digital Companion. Self-hosted Telegram bot orchestrating multiple AI providers (OpenAI, Anthropic, Googl

  • mcp-gateway by lasso-security · ⭐ 403

    A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade ag

  • claude-context-local by FarhanAliRaza · ⭐ 238

    Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created

  • comfy-pilot by ConstantineB6 · ⭐ 232

    MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows

  • mcp-image by shinpr · ⭐ 190

    MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools