Menu
SkillsMP a collecté 63 skills depuis InternScience/MolClaw. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 63.
All tools utilized within MolClaw skills connect via the MCP protocol. This skill is the unified guide for connecting to the deployed MCP server before invoking tools.
Langue du texte source : anglais
Formats extracted execution patterns into standard MolClaw skill documents. Accepts structured input from the Skill Crystallization Meta-Workflow (L2-12) and outputs a properly formatted L1 or L2 skill document conforming to MolClaw conventions. This skill…
Langue du texte source : anglais
Predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.
Langue du texte source : anglais
Predict binding affinity between target protein sequence and small molecule SMILES using Boltz-2.
Langue du texte source : anglais
Retrieve SMILES strings by compound name using PubChem with an NCI resolver fallback.
Langue du texte source : anglais
Generate new molecules de novo.
Langue du texte source : anglais
End-to-end docking-score ranking using EquiScore for candidate molecules against a target protein.
Langue du texte source : anglais
Repair and clean PDB or mmCIF structures with PDBFixer, returning a repaired PDB path and topology counts.
Langue du texte source : anglais
Run GoCa coarse-grained protein MD pipeline and collect key simulation artifacts from a unified run directory.
Langue du texte source : anglais
Run HDOCKlite docking for protein complexes and return run directories with ranked models.
Langue du texte source : anglais
**PRIMARY tool for all single-structure interaction analysis.** MCP-exposed protein–ligand / peptide / protein–protein interaction analysis and Schrödinger-style multi-dimensional visualization. Pure Python/NumPy engine covering 9 interaction types with 2D…
Langue du texte source : anglais
Generate new molecules sampling from the input two warhead fragments.
Langue du texte source : anglais
Calculate both Tanimoto similarities and the count of shared structural fragments between a target molecule and a list of candidate molecules via Morgan fingerprints.
Langue du texte source : anglais
Generate new molecules sampling from the input molecule.
Langue du texte source : anglais
Runs OpenAWSEM simulations and extracts representative trajectory frames for downstream ensemble analysis.
Langue du texte source : anglais
Repair a protein PDB or mmCIF structure with PDBFixer and write a repaired PDB.
Langue du texte source : anglais
Generate new peptide molecules sampling from the input peptide sequence.
Langue du texte source : anglais
Execution-ready protein-ligand MM/GB(PB)SA workflow with explicit MCP handoffs and optional analysis.
Langue du texte source : anglais
Run OpenMM protein MD and extract evenly spaced trajectory frames for downstream structural analysis.
Langue du texte source : anglais
Execution-ready protein-protein MM/GB(PB)SA workflow with MCP-exposed tool names, strict file validation, and failure guards.
Langue du texte source : anglais
Search the target protein sequence information from the input gene name or uniprot id.
Langue du texte source : anglais
Retrieve and download a protein structure file (.pdb or .cif) using a gene name, UniProt ID, or PDB ID.
Langue du texte source : anglais
Perform molecular docking using QuickVina2-GPU between target protein structure and small molecules.
Langue du texte source : anglais
Generate new molecules sampling from the input scaffold.
Langue du texte source : anglais
Run BioEmu sequence sampling and extract ensemble structures for downstream conformation analysis.
Langue du texte source : anglais
Render a molecule from a SMILES string or a server-side molecular structure file with the MolClaw MCP tool `visualize_molecule`.
Langue du texte source : anglais
Render a server-side PDB protein structure as a PNG with the MolClaw MCP tool `visualize_protein`.
Langue du texte source : anglais
Predict protein structures with Chai-1 from sequence or FASTA input and return model scoring summaries.
Langue du texte source : anglais
Chroma toolkit skill covering chroma_monomer for single-chain generation, chroma_complex for multi-chain assembly generation, and chroma_symmetry for symmetry-constrained protein design.
Langue du texte source : anglais
[CURRENTLY UNAVAILABLE] DiffDock protein-ligand docking. This tool is not deployed on the current MCP server. Use molclaw-quickvina-docking or molclaw-karmadock-tool as alternatives.
Langue du texte source : anglais
Calculate disease reversal scores for the provided molecules relative to a specific disease.
Langue du texte source : anglais
High-level large-scale virtual screening workflow (10+ ligands) combining property filtering, QuickVina docking, EquiScore rescoring, and consensus ranking for target prioritization.
Langue du texte source : anglais
Compute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate molecules (SMILES format).
Langue du texte source : anglais
Unified EquiScore skill for pocket extraction, pocket scoring, and end-to-end docking-to-score pipeline execution.
Langue du texte source : anglais
Use ESMFold model to predict 3D structure of the input protein sequence.
Langue du texte source : anglais
Design linear or cyclic peptide binders from receptor FASTA sequences using EvoBind2 with structured result outputs.
Langue du texte source : anglais
Extract protein sequence of each chain from the protein structure file (pdb format).
Langue du texte source : anglais
Implement data transmission between the local computer and the MCP Server using Base64 encoding
Langue du texte source : anglais
FoldX protein stability and mutation analysis tool. Supports 8 modes: structure repair (RepairPDB), stability calculation (Stability), mutation ΔΔG (BuildModel), complex interface energy (AnalyseComplex), alanine scanning (AlaScan), position scanning…
Langue du texte source : anglais
Use fpocket to detect binding pockets and output their detailed properties for the input protein. This offers a more concise approach to pocket identification.
Langue du texte source : anglais