InternScience/MolClaw

molclaw-scp-server

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.

molclaw-skill-template-writer

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…

molclaw-admet

Predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.

molclaw-boltz2-affinity

Predict binding affinity between target protein sequence and small molecule SMILES using Boltz-2.

molclaw-compound-retrieve

Retrieve SMILES strings by compound name using PubChem with an NCI resolver fallback.

molclaw-denovo-sampling

Generate new molecules de novo.

molclaw-equiscore-docking

End-to-end docking-score ranking using EquiScore for candidate molecules against a target protein.

molclaw-fix-pdb

Repair and clean PDB or mmCIF structures with PDBFixer, returning a repaired PDB path and topology counts.

molclaw-goca-tool

Run GoCa coarse-grained protein MD pipeline and collect key simulation artifacts from a unified run directory.

molclaw-hdock-tool

Run HDOCKlite docking for protein complexes and return run directories with ranked models.

molclaw-interaction-visualizer

**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…

molclaw-linker-sampling

Generate new molecules sampling from the input two warhead fragments.

molclaw-mol-similarity

Calculate both Tanimoto similarities and the count of shared structural fragments between a target molecule and a list of candidate molecules via Morgan fingerprints.

molclaw-mol2mol-sampling

Generate new molecules sampling from the input molecule.

molclaw-openawsem-tool

Runs OpenAWSEM simulations and extracts representative trajectory frames for downstream ensemble analysis.

molclaw-pdbfixer

Repair a protein PDB or mmCIF structure with PDBFixer and write a repaired PDB.

molclaw-peptide-sampling

Generate new peptide molecules sampling from the input peptide sequence.

molclaw-protein-ligand-mmpbsa

Execution-ready protein-ligand MM/GB(PB)SA workflow with explicit MCP handoffs and optional analysis.

molclaw-protein-openmm

Run OpenMM protein MD and extract evenly spaced trajectory frames for downstream structural analysis.

molclaw-protein-protein-mmpbsa

Execution-ready protein-protein MM/GB(PB)SA workflow with MCP-exposed tool names, strict file validation, and failure guards.

molclaw-protein-sequence-retrieve

Search the target protein sequence information from the input gene name or uniprot id.

molclaw-protein-structure-retrieve

Retrieve and download a protein structure file (.pdb or .cif) using a gene name, UniProt ID, or PDB ID.

molclaw-quickvina-docking

Perform molecular docking using QuickVina2-GPU between target protein structure and small molecules.

molclaw-rgroup-sampling

Generate new molecules sampling from the input scaffold.

molclaw-run-bioemu

Run BioEmu sequence sampling and extract ensemble structures for downstream conformation analysis.

molclaw-visualize-molecule

Render a molecule from a SMILES string or a server-side molecular structure file with the MolClaw MCP tool `visualize_molecule`.

molclaw-visualize-protein

Render a server-side PDB protein structure as a PNG with the MolClaw MCP tool `visualize_protein`.

molclaw-chai1-predict

Predict protein structures with Chai-1 from sequence or FASTA input and return model scoring summaries.

molclaw-chroma-toolkit

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.

molclaw-diffdock-auto

[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.

molclaw-dleps

Calculate disease reversal scores for the provided molecules relative to a specific disease.

molclaw-docking-screening

High-level large-scale virtual screening workflow (10+ ligands) combining property filtering, QuickVina docking, EquiScore rescoring, and consensus ranking for target prioritization.

molclaw-drug-likeness

Compute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate molecules (SMILES format).

molclaw-equiscore-tool

Unified EquiScore skill for pocket extraction, pocket scoring, and end-to-end docking-to-score pipeline execution.

molclaw-esmfold

Use ESMFold model to predict 3D structure of the input protein sequence.

molclaw-evobind-tool

Design linear or cyclic peptide binders from receptor FASTA sequences using EvoBind2 with structured result outputs.

molclaw-extract-chains

Extract protein sequence of each chain from the protein structure file (pdb format).

molclaw-file-transfer

Implement data transmission between the local computer and the MCP Server using Base64 encoding

molclaw-foldx-tool

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…

molclaw-fpocket

Use fpocket to detect binding pockets and output their detailed properties for the input protein. This offers a more concise approach to pocket identification.