PaperBanana: MCP server, setup and security

What PaperBanana does

According to its repository: “Generate academic diagrams and statistical plots from text using multi-agent AI.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. PaperBanana is listed under Data science and visualization, a category of 48 servers in the directory, where it ranks #8 by stars.

Topics declared by the repository: academic-research, arxiv, gemini, llms, multiagent, neurips.

Installing and connecting PaperBanana

Distribution modes declared in the official MCP registry:

• PyPI package (Python, started with uvx or pip)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to PaperBanana. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 4, 2026, the llmsresearch/paperbanana repository has 2,417 stars and 342 forks, with 2 open issues. It has more stars than 95% of the servers in the directory. Last change 1 month ago. Version published in the registry: 0.1.1 (February 5, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.