paperbanana — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by llmsresearch · MCP Server · ★ 2.4k

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

🔒 Is paperbanana safe to install? View the security audit →

About paperbanana

PaperBanana Automated Academic Illustration for AI Scientists <img src="https://img.shields.io/badge/license-M

academic-diagramsacademic-researchagentic-aiarxivdiagram-generationgeminigoogle-geminillmllmsmcp

Quick Facts

Stars2,365
Forks334
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score66.4750296775235/100
Open Issues10
Last Updated2026-09-17
Created2026-02-04
Platformsgemini, mcp, python
Est. Tokens~19k

Compatible Skills

These tools work well together with paperbanana for enhanced workflows:

  • open-webui-tools — semantic(0.29)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • local-deep-research — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • rigorous — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (55%)
  • research-units-pipeline-skills — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (55%)
  • sgr-agent-core — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)

paperbanana alternative? Top 6 similar tools

Looking for a paperbanana alternative? If you're comparing paperbanana 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.

  • bytebot by bytebot-ai · ⭐ 11.1k

    Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, ope

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • ag2 by ag2ai · ⭐ 5.0k

    AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

  • Unity-MCP by IvanMurzak · ⭐ 4.3k

    AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Effici

  • agentic-radar by splx-ai · ⭐ 1.1k

    A security scanner for your LLM agentic workflows

  • open-webui-tools by Haervwe · ⭐ 801

    Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is paperbanana?

paperbanana is Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.. It is categorized as a MCP Server with 2.4k GitHub stars.

What programming language is paperbanana written in?

paperbanana is primarily written in Python. It covers topics such as academic-diagrams, academic-research, agentic-ai.

How do I install or use paperbanana?

You can find installation instructions and usage details in the paperbanana GitHub repository at github.com/llmsresearch/paperbanana. The project has 2.4k stars and 334 forks, indicating an active community.

What license does paperbanana use?

paperbanana is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to paperbanana?

The top alternatives to paperbanana on Agent Skills Hub include bytebot, cursor-talk-to-figma-mcp, ag2. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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