ToolUniverse
Overview
ToolUniverse is a unified ecosystem that enables AI agents to function as research scientists by providing standardized access to 600+ scientific resources. Use this skill to discover, execute, and compose scientific tools across multiple research domains including bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.
Key Capabilities:
- Access 600+ scientific tools, models, datasets, and APIs
- Discover tools using natural language, semantic search, or keywords
- Execute tools through standardized AI-Tool Interaction Protocol
- Compose multi-step workflows for complex research problems
- Integration with Claude Desktop/Code via Model Context Protocol (MCP)
When to Use This Skill
Use this skill when:
- Searching for scientific tools by function or domain (e.g., "find protein structure prediction tools")
- Executing computational biology workflows (e.g., disease target identification, drug discovery, genomics analysis)
- Accessing scientific databases (OpenTargets, PubChem, UniProt, PDB, ChEMBL, KEGG, etc.)
- Composing multi-step research pipelines (e.g., target discovery → structure prediction → virtual screening)
- Working with bioinformatics, cheminformatics, or structural biology tasks
- Analyzing gene expression, protein sequences, molecular structures, or clinical data
- Performing literature searches, pathway enrichment, or variant annotation
- Building automated scientific research workflows
Quick Start
Basic Setup
from tooluniverse import ToolUniverse
# Initialize and load tools
tu = ToolUniverse()
tu.load_tools() # Loads 600+ scientific tools
# Discover tools
tools = tu.run({
"name": "Tool_Finder_Keyword",
"arguments": {
"description": "disease target associations",
"limit": 10
}
})
# Execute a tool
result = tu.run({
"name": "OpenTargets_get_associated_targets_by_disease_efoId",
"arguments": {"efoId": "EFO_0000537"} # Hypertension
})
Model Context Protocol (MCP)
For Claude Desktop/Code integration:
tooluniverse-smcp
Core Workflows
1. Tool Discovery
Find relevant tools for your research task:
Three discovery methods:
Tool_Finder - Embedding-based semantic search (requires GPU)
Tool_Finder_LLM - LLM-based semantic search (no GPU required)
Tool_Finder_Keyword - Fast keyword search
Example:
# Search by natural language description
tools = tu.run({
"name": "Tool_Finder_LLM",
"arguments": {
"description": "Find tools for RNA sequencing differential expression analysis",
"limit": 10
}
})
# Review available tools
for tool in tools:
print(f"{tool['name']}: {tool['description']}")
See references/tool-discovery.md for:
- Detailed discovery methods and search strategies
- Domain-specific keyword suggestions
- Best practices for finding tools
2. Tool Execution
Execute individual tools through the standardized interface:
Example:
# Execute disease-target lookup
targets = tu.run({
"name": "OpenTargets_get_associated_targets_by_disease_efoId",
"arguments": {"efoId": "EFO_0000616"} # Breast cancer
})
# Get protein structure
structure = tu.run({
"name": "AlphaFold_get_structure",
"arguments": {"uniprot_id": "P12345"}
})
# Calculate molecular properties
properties = tu.run({
"name": "RDKit_calculate_descriptors",
"arguments": {"smiles": "CCO"} # Ethanol
})
See references/tool-execution.md for:
- Real-world execution examples across domains
- Tool parameter handling and validation
- Result processing and error handling
- Best practices for production use
3. Tool Composition and Workflows
Compose multiple tools for complex research workflows:
Drug Discovery Example:
# 1. Find disease targets
targets = tu.run({
"name": "OpenTargets_get_associated_targets_by_disease_efoId",
"arguments": {"efoId": "EFO_0000616"}
})
# 2. Get protein structures
structures = []
for target in targets[:5]:
structure = tu.run({
"name": "AlphaFold_get_structure",
"arguments": {"uniprot_id": target['uniprot_id']}
})
structures.append(structure)
# 3. Screen compounds
hits = []
for structure in structures:
compounds = tu.run({
"name": "ZINC_virtual_screening",
"arguments": {
"structure": structure,
"library": "lead-like",
"top_n": 100
}
})
hits.extend(compounds)
# 4. Evaluate drug-likeness
drug_candidates = []
for compound in hits:
props = tu.run({
"name": "RDKit_calculate_drug_properties",
"arguments": {"smiles": compound['smiles']}
})
if props['lipinski_pass']:
drug_candidates.append(compound)
See references/tool-composition.md for:
- Complete workflow examples (drug discovery, genomics, clinical)
- Sequential and parallel tool composition patterns
- Output processing hooks
- Workflow best practices
Scientific Domains
ToolUniverse supports 600+ tools across major scientific domains:
Bioinformatics:
- Sequence analysis, alignment, BLAST
- Gene expression (RNA-seq, DESeq2)
- Pathway enrichment (KEGG, Reactome, GO)
- Variant annotation (VEP, ClinVar)
Cheminformatics:
- Molecular descriptors and fingerprints
- Drug discovery and virtual screening
- ADMET prediction and drug-likeness
- Chemical databases (PubChem, ChEMBL, ZINC)
Structural Biology:
- Protein structure prediction (AlphaFold)
- Structure retrieval (PDB)
- Binding site detection
- Protein-protein interactions
Proteomics:
- Mass spectrometry analysis
- Protein databases (UniProt, STRING)
- Post-translational modifications
Genomics:
- Genome assembly and annotation
- Copy number variation
- Clinical genomics workflows
Medical/Clinical:
- Disease databases (OpenTargets, OMIM)
- Clinical trials and FDA data
- Variant classification
See references/domains.md for:
- Complete domain categorization
- Tool examples by discipline
- Cross-domain applications
- Search strategies by domain
Reference Documentation
This skill includes comprehensive reference files that provide detailed information for specific aspects:
references/installation.md - Installation, setup, MCP configuration, platform integration
references/tool-discovery.md - Discovery methods, search strategies, listing tools
references/tool-execution.md - Execution patterns, real-world examples, error handling
references/tool-composition.md - Workflow composition, complex pipelines, parallel execution
references/domains.md - Tool categorization by domain, use case examples
references/api_reference.md - Python API documentation, hooks, protocols
Workflow: When helping with specific tasks, reference the appropriate file for detailed instructions. For example, if searching for tools, consult references/tool-discovery.md for search strategies.
Example Scripts
Two executable example scripts demonstrate common use cases:
scripts/example_tool_search.py - Demonstrates all three discovery methods:
- Keyword-based search
- LLM-based search
- Domain-specific searches
- Getting detailed tool information
scripts/example_workflow.py - Complete workflow examples:
- Drug discovery pipeline (disease → targets → structures → screening → candidates)
- Genomics analysis (expression data → differential analysis → pathways)
Run examples to understand typical usage patterns and workflow composition.
Best Practices
Tool Discovery:
- Start with broad searches, then refine based on results
- Use
Tool_Finder_Keyword for fast searches with known terms
- Use
Tool_Finder_LLM for complex semantic queries
- Set appropriate
limit parameter (default: 10)
Tool Execution:
- Always verify tool parameters before execution
- Implement error handling for production workflows
- Validate input data formats (SMILES, UniProt IDs, gene symbols)
- Check result types and structures
Workflow Composition:
- Test each step individually before composing full workflows
- Implement checkpointing for long workflows
- Consider rate limits for remote APIs
- Use parallel execution when tools are independent
Integration:
- Initialize ToolUniverse once and reuse the instance
- Call
load_tools() once at startup
- Cache frequently used tool information
- Enable logging for debugging
Key Terminology
- Tool: A scientific resource (model, dataset, API, package) accessible through ToolUniverse
- Tool Discovery: Finding relevant tools using search methods (Finder, LLM, Keyword)
- Tool Execution: Running a tool with specific arguments via
tu.run()
- Tool Composition: Chaining multiple tools for multi-step workflows
- MCP: Model Context Protocol for integration with Claude Desktop/Code
- AI-Tool Interaction Protocol: Standardized interface for LLM-tool communication
Resources
1---2name: "tooluniverse"3description: "Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides acces"4metadata:5 source: https://skillmd.com/skills/viggyv/tooluniverse6---78# ToolUniverse910## Overview1112ToolUniverse is a unified ecosystem that enables AI agents to function as research scientists by providing standardized access to 600+ scientific resources. Use this skill to discover, execute, and compose scientific tools across multiple research domains including bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.1314**Key Capabilities:**15- Access 600+ scientific tools, models, datasets, and APIs16- Discover tools using natural language, semantic search, or keywords17- Execute tools through standardized AI-Tool Interaction Protocol18- Compose multi-step workflows for complex research problems19- Integration with Claude Desktop/Code via Model Context Protocol (MCP)2021## When to Use This Skill2223Use this skill when:24- Searching for scientific tools by function or domain (e.g., "find protein structure prediction tools")25- Executing computational biology workflows (e.g., disease target identification, drug discovery, genomics analysis)26- Accessing scientific databases (OpenTargets, PubChem, UniProt, PDB, ChEMBL, KEGG, etc.)27- Composing multi-step research pipelines (e.g., target discovery → structure prediction → virtual screening)28- Working with bioinformatics, cheminformatics, or structural biology tasks29- Analyzing gene expression, protein sequences, molecular structures, or clinical data30- Performing literature searches, pathway enrichment, or variant annotation31- Building automated scientific research workflows3233## Quick Start3435### Basic Setup36```python37from tooluniverse import ToolUniverse3839# Initialize and load tools40tu = ToolUniverse()41tu.load_tools() # Loads 600+ scientific tools4243# Discover tools44tools = tu.run({45 "name": "Tool_Finder_Keyword",46 "arguments": {47 "description": "disease target associations",48 "limit": 1049 }50})5152# Execute a tool53result = tu.run({54 "name": "OpenTargets_get_associated_targets_by_disease_efoId",55 "arguments": {"efoId": "EFO_0000537"} # Hypertension56})57```5859### Model Context Protocol (MCP)60For Claude Desktop/Code integration:61```bash62tooluniverse-smcp63```6465## Core Workflows6667### 1. Tool Discovery6869Find relevant tools for your research task:7071**Three discovery methods:**72- `Tool_Finder` - Embedding-based semantic search (requires GPU)73- `Tool_Finder_LLM` - LLM-based semantic search (no GPU required)74- `Tool_Finder_Keyword` - Fast keyword search7576**Example:**77```python78# Search by natural language description79tools = tu.run({80 "name": "Tool_Finder_LLM",81 "arguments": {82 "description": "Find tools for RNA sequencing differential expression analysis",83 "limit": 1084 }85})8687# Review available tools88for tool in tools:89 print(f"{tool['name']}: {tool['description']}")90```9192**See `references/tool-discovery.md` for:**93- Detailed discovery methods and search strategies94- Domain-specific keyword suggestions95- Best practices for finding tools9697### 2. Tool Execution9899Execute individual tools through the standardized interface:100101**Example:**102```python103# Execute disease-target lookup104targets = tu.run({105 "name": "OpenTargets_get_associated_targets_by_disease_efoId",106 "arguments": {"efoId": "EFO_0000616"} # Breast cancer107})108109# Get protein structure110structure = tu.run({111 "name": "AlphaFold_get_structure",112 "arguments": {"uniprot_id": "P12345"}113})114115# Calculate molecular properties116properties = tu.run({117 "name": "RDKit_calculate_descriptors",118 "arguments": {"smiles": "CCO"} # Ethanol119})120```121122**See `references/tool-execution.md` for:**123- Real-world execution examples across domains124- Tool parameter handling and validation125- Result processing and error handling126- Best practices for production use127128### 3. Tool Composition and Workflows129130Compose multiple tools for complex research workflows:131132**Drug Discovery Example:**133```python134# 1. Find disease targets135targets = tu.run({136 "name": "OpenTargets_get_associated_targets_by_disease_efoId",137 "arguments": {"efoId": "EFO_0000616"}138})139140# 2. Get protein structures141structures = []142for target in targets[:5]:143 structure = tu.run({144 "name": "AlphaFold_get_structure",145 "arguments": {"uniprot_id": target['uniprot_id']}146 })147 structures.append(structure)148149# 3. Screen compounds150hits = []151for structure in structures:152 compounds = tu.run({153 "name": "ZINC_virtual_screening",154 "arguments": {155 "structure": structure,156 "library": "lead-like",157 "top_n": 100158 }159 })160 hits.extend(compounds)161162# 4. Evaluate drug-likeness163drug_candidates = []164for compound in hits:165 props = tu.run({166 "name": "RDKit_calculate_drug_properties",167 "arguments": {"smiles": compound['smiles']}168 })169 if props['lipinski_pass']:170 drug_candidates.append(compound)171```172173**See `references/tool-composition.md` for:**174- Complete workflow examples (drug discovery, genomics, clinical)175- Sequential and parallel tool composition patterns176- Output processing hooks177- Workflow best practices178179## Scientific Domains180181ToolUniverse supports 600+ tools across major scientific domains:182183**Bioinformatics:**184- Sequence analysis, alignment, BLAST185- Gene expression (RNA-seq, DESeq2)186- Pathway enrichment (KEGG, Reactome, GO)187- Variant annotation (VEP, ClinVar)188189**Cheminformatics:**190- Molecular descriptors and fingerprints191- Drug discovery and virtual screening192- ADMET prediction and drug-likeness193- Chemical databases (PubChem, ChEMBL, ZINC)194195**Structural Biology:**196- Protein structure prediction (AlphaFold)197- Structure retrieval (PDB)198- Binding site detection199- Protein-protein interactions200201**Proteomics:**202- Mass spectrometry analysis203- Protein databases (UniProt, STRING)204- Post-translational modifications205206**Genomics:**207- Genome assembly and annotation208- Copy number variation209- Clinical genomics workflows210211**Medical/Clinical:**212- Disease databases (OpenTargets, OMIM)213- Clinical trials and FDA data214- Variant classification215216**See `references/domains.md` for:**217- Complete domain categorization218- Tool examples by discipline219- Cross-domain applications220- Search strategies by domain221222## Reference Documentation223224This skill includes comprehensive reference files that provide detailed information for specific aspects:225226- **`references/installation.md`** - Installation, setup, MCP configuration, platform integration227- **`references/tool-discovery.md`** - Discovery methods, search strategies, listing tools228- **`references/tool-execution.md`** - Execution patterns, real-world examples, error handling229- **`references/tool-composition.md`** - Workflow composition, complex pipelines, parallel execution230- **`references/domains.md`** - Tool categorization by domain, use case examples231- **`references/api_reference.md`** - Python API documentation, hooks, protocols232233**Workflow:** When helping with specific tasks, reference the appropriate file for detailed instructions. For example, if searching for tools, consult `references/tool-discovery.md` for search strategies.234235## Example Scripts236237Two executable example scripts demonstrate common use cases:238239**`scripts/example_tool_search.py`** - Demonstrates all three discovery methods:240- Keyword-based search241- LLM-based search242- Domain-specific searches243- Getting detailed tool information244245**`scripts/example_workflow.py`** - Complete workflow examples:246- Drug discovery pipeline (disease → targets → structures → screening → candidates)247- Genomics analysis (expression data → differential analysis → pathways)248249Run examples to understand typical usage patterns and workflow composition.250251## Best Practices2522531. **Tool Discovery:**254 - Start with broad searches, then refine based on results255 - Use `Tool_Finder_Keyword` for fast searches with known terms256 - Use `Tool_Finder_LLM` for complex semantic queries257 - Set appropriate `limit` parameter (default: 10)2582592. **Tool Execution:**260 - Always verify tool parameters before execution261 - Implement error handling for production workflows262 - Validate input data formats (SMILES, UniProt IDs, gene symbols)263 - Check result types and structures2642653. **Workflow Composition:**266 - Test each step individually before composing full workflows267 - Implement checkpointing for long workflows268 - Consider rate limits for remote APIs269 - Use parallel execution when tools are independent2702714. **Integration:**272 - Initialize ToolUniverse once and reuse the instance273 - Call `load_tools()` once at startup274 - Cache frequently used tool information275 - Enable logging for debugging276277## Key Terminology278279- **Tool**: A scientific resource (model, dataset, API, package) accessible through ToolUniverse280- **Tool Discovery**: Finding relevant tools using search methods (Finder, LLM, Keyword)281- **Tool Execution**: Running a tool with specific arguments via `tu.run()`282- **Tool Composition**: Chaining multiple tools for multi-step workflows283- **MCP**: Model Context Protocol for integration with Claude Desktop/Code284- **AI-Tool Interaction Protocol**: Standardized interface for LLM-tool communication285286## Resources287288- **Official Website**: https://aiscientist.tools289- **GitHub**: https://github.com/mims-harvard/ToolUniverse290- **Documentation**: https://zitniklab.hms.harvard.edu/ToolUniverse/291- **Installation**: `uv uv pip install tooluniverse`292- **MCP Server**: `tooluniverse-smcp`