AgentSidekick

Scientific Computing

Domain tools for biology, chemistry and math. As of 2026-11-21, 112 indexed products offer it (23 with full profiles), in 4 forms: 100 MCP servers, 10 Agent skills, 1 Infrastructure, 1 Rules pack. 44 were published in the last 90 days, against 31 in the 90 days before. scientific-agent-skills has the most GitHub stars, 91% of the total across 85 products with their own repository.

CapabilitySegment label: Lagging the catalogue DER

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 100 indexed · 12 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Scientific Computing: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1MirobodyLab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.thetahealth.ai1.6k1d ago
2biomcpBioMCP: Biomedical Model Context Protocolgenomoncology68311d ago
3pubmed-mcp-serverSearch PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.cyanheads1698d ago
4operonAI-powered IDE for bioinformatics — built by biologists, for biologistsswaruplab1041mo ago
5clinicaltrialsgov-mcp-serverSearch ClinicalTrials.gov: find studies, retrieve results, match patients to candidate trials.cyanheads1028d ago
6ChatSpatialSchema-enforced spatial transcriptomics analysis with 20 tools and 67 methods via MCPcafferychen777491mo ago
7galaxy-mcpMCP server for Galaxy bioinformatics platform - connect, execute tools, and manage workflowsgalaxyproject402d ago
8ChemDraw MCP (unofficial)Molecule names or SMILES to 2D structures, reactions, mechanisms, spectra - drawn locally by RDKit.jurimaxam-dotcom32today
9ENCODE Toolkit20 MCP tools + 48 skills for ENCODE Project genomics — search, download, pipelinesammawla201mo ago
10Dense EvolutionReal quantum circuit simulator, VQE, molecular Hamiltonians, QM/MM forces, and MD via 21 tools.tatopenn-cell204d ago

All 12 profiled MCP servers with this capability

Agent skills 10 indexed · 10 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Scientific Computing: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1scientific-agent-skillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.K-Dense-AI58k5d ago
2SciAgent-Skills197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon.jaechang-hits3955d ago
3biopythonProvides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.K-Dense-AI—5d ago
4bioservicesProvides a Python interface to bioinformatics services including UniProt, KEGG, ChEMBL, Reactome, QuickGO, and UniChem. Used for cross-database protein annotation, pathway retrieval, chemical identifier mapping, and integrated biological data workflows with BioServices.K-Dense-AI—5d ago
5diffdockPredicts protein-small-molecule binding poses with DiffDock and DiffDock-L from PDB or sequence plus SMILES/SDF/MOL2. Covers batch docking, pose triage, confidence interpretation, and validation. Use for molecular docking and virtual-screening pose generation, not binding-affinity prediction.K-Dense-AI—5d ago
6deepchemBuilds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for ADMET, toxicity, solubility and chemistry ML when DeepChem data/model contracts and scientific validation are needed.K-Dense-AI—5d ago
7dnanexus-integrationBuilds and operates reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Supports DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.K-Dense-AI—5d ago
8ggetQueries 20+ bioinformatics resources through CLI/Python. Supports quick lookups of gene info, BLAST/BLAT, viral sequence downloads, PDB/mmCIF structures, G2P residue annotations, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.K-Dense-AI—5d ago
9hugging-scienceDiscovers and evaluates scientific datasets, models, methodology posts, and Spaces through the Hugging Science catalog. Used when selecting scientific ML resources in biology, chemistry, genomics, materials, climate, physics, astronomy, medicine, mathematics, protein design, single-cell analysis, or PDE modeling, and when checking their actual datasets, Transformers, native-runtime, Inference Providers, or Gradio interfaces.K-Dense-AI—5d ago
10ml-training-recipesBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.Orchestra-Research—1mo ago

Infrastructure 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Scientific Computing: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1bootcampDealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.milvus-io2.5k1mo ago

Rules packs 1 indexed · 0 profiled

No compatibility evidence is collected for this form.

1 indexed, none with a full profile yet.

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code2
Cursor1
Google Antigravity1
Codex1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
Obsidian10.9%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
bioinformatics48
chemistry30
protein structure2
molecular14
genomics15
computational biology2
wolfram alpha1

Segment statistics

Whole catalogue (112 indexed products). Calculated 2026-11-21.

112DERIndexed products23 with full profiles
44DERLaunched, last 90 days31 in the 90 days before
17DERMomentum vs catalogue50 = same pace as the catalogue
91%DERLargest project's share of starsAcross 85 products with their own repository
0.826DERConcentration (HHI)About 1 equal-sized projects’ worth; highly concentrated
1SRCMedian starsPer product with its own repository
74%DEROpen sourceMarked open source; unknown counts as not

Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.826 means stars are spread as if across about 1 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .