Claude security directory

ToolUniverse

Published by ToolUniverse Team

High risk

ToolUniverse is a research-focused MCP bundle that connects Claude to a wide catalog of scientific databases, APIs, and machine learning models for life sciences and bioinformatics workflows. It targets researchers building AI-driven scientific assistants.

Security assessment

Plutonium assessed this desktop extension for permissions, capabilities, and security-relevant behavior.

  • Can run commands or queries on your behalf: ToolUniverse ships python_code_executor and python_script_runner - explicit Python execution tools. python_code_executor uses an AST-walk whitelist sandbox; python_script_runner runs in a subprocess. The package also includes an `auto_install` feature that pip-installs arbitrary packages on demand. Python AST sandboxes are well-known to be bypassable in…
  • Sends your data to many third-party services: ToolUniverse exposes 2,155 tools across 200+ external scientific databases (NCBI, FDA, NVIDIA, ChEMBL, UniProt, BioGRID, ClinicalTrials.gov, OncoKB, OMIM, UMLS, …). Each query is routed to whichever underlying service the model picks, and each service has its own logging, retention, and terms.
  • Sends content to a separate LLM provider on your behalf: 23 'agentic' tools call OpenAI (or another LLM) using your OPENAI_API_KEY. Anything you feed those tools is shipped to that LLM and may be retained per their terms.
  • Reads your private information: Inputs to scientific queries - patient identifiers, gene symbols, compound names, study details - flow through the connector's tools to whichever underlying service the model picks.

Available capabilities

This add-on exposes 29 tools or capabilities.

  • list_tools
  • grep_tools
  • get_tool_info
  • execute_tool
  • python_code_executor
  • python_script_runner
  • AdvancedCodeQualityAnalyzer
  • DataAnalysisValidityReviewer
  • DomainExpertValidator
  • EthicalComplianceReviewer
  • ExperimentalDesignScorer
  • HypothesisGenerator
  • LabelGenerator
  • LiteratureContextReviewer
  • MedicalLiteratureReviewer
  • MedicalTermNormalizer
  • MethodologyRigorReviewer
  • NoveltySignificanceReviewer
  • ProtocolOptimizer
  • QuestionRephraser
  • ReproducibilityTransparencyReviewer
  • ResultsInterpretationReviewer
  • ScientificTextSummarizer
  • ToolMetadataGenerator

The interactive security report will load automatically.