tooluniverse

Side-by-side comparison of N items (drugs, targets, diseases, variants, trials, etc.) with a domain-appropriate column set, structured tabular output, and per-cell source citation. Use when the user wants to evaluate alternatives, not when they want a profile of a single item. Enforces the comparison structure that ad-hoc research doesn't.

Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.

Run a graded mini-review on a topic across many literature sources, adaptively chosen by domain — a core multi-field set (PubMed, EuropePMC, OpenAlex, Semantic Scholar) plus domain-specific indexes (ArXiv/DBLP for CS, InspireHEP for physics, PubTator/PMC/clinical guidelines for biomedical, Crossref/CORE/DOAJ/Fatcat for broad coverage, OSF/preprints for the latest work). Dedupes hits, scores relevance to the topic, returns a ranked table with citation, year, key claim, and relevance. Use when the user wants more than a raw search dump — they want a curated short-list ready to read.

Conduct a multi-database scientific research investigation inline in the current chat. Same operating discipline as the /tooluniverse:researcher agent (look up specific claims, cross-validate, honest INDETERMINATE) — but runs in this conversation so you can watch each step, follow up, and refine, instead of receiving a single summary from a forked subagent. Use when you want to drive the research yourself with ToolUniverse rather than delegating to a subagent.

Generate the success criteria for a task or question, then review work against them. Decomposes the task into scenarios → evaluation perspectives → weighted YES/NO criteria (the Qworld Recursive Expansion Tree method) and, if you supply the work, scores it criterion-by-criterion and lists what is missing or could be better. Use to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done / completeness checklist, or create an evaluation rubric / grading criteria for answers to a question.

Autonomous scientific research agent with access to 1000+ databases. Use for complex research questions that require searching multiple databases, analyzing data, and synthesizing findings.

Install and configure ToolUniverse for any use case — MCP server (chat-based), CLI (command line with 9 subcommands), or Python SDK (Coding API with 3 calling patterns). Covers uv/uvx setup, MCP configuration for 12+ AI clients (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, etc.), full CLI reference (tu list/grep/find/info/run/test/status/build/serve), Coding API quickstart, agentic tools, code executor, API key walkthrough, skill installation, and upgrading. Use when user asks how to set up ToolUniverse, which access mode to use (MCP vs CLI vs SDK), configuring MCP servers, using the CLI, troubleshooting installation, upgrading, or mentions installing ToolUniverse or setting up scientific tools. Also triggers for "how do I use ToolUniverse", "what's the best way to access tools", "command line", "tu command", "coding API", "tu build".

Systematic ACMG/AMP germline variant classification with all 28 criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7) for clinical significance. Produces 5-tier verdict (Pathogenic / Likely Pathogenic / VUS / Likely Benign / Benign) with cited evidence per criterion. Use for variant interpretation, VUS resolution, and pathogenicity assessment. Combines ClinVar, gnomAD, computational predictors, and gene-mechanism context.

Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling for drug candidates. Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data. Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries before lab testing.

Detect and analyze adverse drug event signals using FDA FAERS reports, drug labels, and disproportionality statistics (PRR, ROR, IC). Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, regulatory submissions, and detecting rare AE signals not visible in clinical trials.

Map environmental and industrial chemicals to adverse outcome pathways (AOPs) — molecular initiating event to organ-level toxicity. Uses AOPWiki, GHS classification, IARC carcinogen status, and LD50 data. Use for environmental/industrial chemical risk assessment, regulatory-grade hazard characterization, and AOP stressor mapping. Distinct from drug-safety analysis (use tooluniverse-pharmacovigilance for drugs).

2 hooks across 1 event