tamarind-mcp
claudecodexRun 300+ Tamarind Bio protein and molecular-science tools through the authenticated MCP server — structure prediction, design, docking, and analysis.
17 skills · 1 MCP server
Run Tamarind Bio biology tools from your agent through the Tamarind CLI.
Plugin tamarind-cli from marketplace tamarind-agent-plugin in Tamarind-Bio/tamarind-agent-plugin. Commands read from the repo's manifest — 9 days ago.
tamarind-antibodyDesign, redesign, model, number, humanize, or search antibodies, nanobodies/VHHs, and TCRs with Tamarind Bio. Use for CDR-aware or repertoire-specific workflows and antibody developability handoffs. Not for general non-antibody binder design, generic complex folding, or developability scoring alone.
tamarind-api-setupInstall, upgrade, authenticate, or troubleshoot the Tamarind CLI before running Tamarind Bio jobs. Use when `tamarind` is missing or incompatible, authentication is absent or rejected, endpoints/profiles need configuration, or a safe no-spend connectivity check is needed. Not for submitting compute
tamarind-batchRun one Tamarind Bio tool across many independent inputs as a tracked batch, then monitor the parent, inspect subjobs, download aggregation, and rank completed results. Use for libraries and screens. Not for one input, multiple dependent tool stages, or an unbounded loop of individual submissions.
tamarind-binder-designDesign new de novo protein, peptide, macrocycle, or small-molecule binders against a target with Tamarind Bio, then refold and rank candidates. Use for backbone/sequence or ligand generation from scratch. Not for antibody-specific CDR engineering, fixed-backbone inverse folding, docking an existing
tamarind-custom-tool-deployConvert a local folder or git repository into the Tamarind Custom Tool format and deploy it through the unified Tamarind CLI. Use when onboarding a model, script, or container so an organization can submit it like a built-in tool. Not for running an existing catalog tool or configuring GitHub push-t
tamarind-developabilityScore protein or antibody candidates for manufacturability and clinic-readiness with Tamarind Bio, including stability, aggregation, solubility, viscosity, polyreactivity, glycosylation, and immunogenicity. Use as a post-design filter. Not for generating molecules, folding structures, or measuring b
tamarind-dockingDock or screen known ligands against a receptor, perform protein-protein docking, or score binding affinity/interface quality from existing structures with Tamarind Bio. Use for pocket-based or blind docking and pose ranking. Not for co-folding from sequence, generating a new ligand or binder, or ge
tamarind-finetuneFine-tune a Tamarind-hosted model on user-provided labeled data and run the matching inference tool with the trained job. Use for supported finetune/inference pairs in protein, affinity, enzyme, or small-molecule workflows. Not for stock pretrained inference, ordinary batch prediction, or unsupporte
tamarind-inverse-foldingDesign sequences for a fixed protein backbone or run protein language models for embeddings, mutation scoring, and sequence generation with Tamarind Bio. Use for ProteinMPNN-, LigandMPNN-, ESM-IF-, or PLM-style tasks. Not for de novo backbone generation, antibody CDR design, or ordinary structure pr
tamarind-miniprotein-campaignRun Anthropic's published de novo miniprotein binder campaign protocol with Tamarind Bio against one target and epitope — multi-method generation under a per-method floor, four pre-scoring gates, a three-arm co-folding instrument frozen and control-validated before any production scoring, five or mo
tamarind-more-toolsDiscover and run Tamarind Bio tools outside the dedicated protein-folding, binder, antibody, docking, inverse-folding, and developability skills. Use for enzyme work, small-molecule properties/QM, molecular dynamics, nucleic acids, cryo-EM, structure search, and format utilities. Not for a domain th
tamarind-pipelineOrchestrate multiple dependent Tamarind Bio tools as a resumable CLI campaign where each successful stage feeds the next, such as design to fold to score. Use when later stages depend on earlier artifacts or metrics. Not for one job or one tool applied independently across many inputs.
tamarind-results-analysisRecover and analyze an existing Tamarind Bio job by name: check or wait for status, inspect logs and metrics, download results, rank scientific outputs, and prepare a downstream input. Use after submission, across sessions, or when a previous command was interrupted. Not for starting a new job or ch
tamarind-structure-predictionPredict or co-fold a protein, peptide, nucleic acid, ligand, or biomolecular complex from sequence with Tamarind Bio. Use for AlphaFold-, Boltz-, Chai-, ESMFold-, or Protenix-style structure prediction and confidence interpretation. Not for de novo binder generation, fixed-backbone sequence design,
tamarind-submit-and-pollRun one known Tamarind Bio tool end to end through the Tamarind CLI: validate settings, confirm consequential choices and spend, submit once, wait with a timeout, inspect terminal status, and download results. Also use to reattach to one already-submitted job. Not for tool selection, batch submissio
tamarind-tool-discoveryChoose which Tamarind Bio tool fits a scientific goal by querying the live CLI catalog and schema. Use when the user has not named a tool, when several tools could fit, or when availability and required inputs must be verified. Not for installing/authenticating the CLI or executing a tool that is al
Run 300+ Tamarind Bio protein and molecular-science tools through the authenticated MCP server — structure prediction, design, docking, and analysis.
17 skills · 1 MCP server
Full Domino Data Lab platform support — workspaces, jobs, model deployment, experiment tracking, GenAI tracing, Spark/Ray/Dask, and app deployment for data science teams
26 skills · 4 commands · 3 agents · 1 MCP server
Evidence-backed BioPharma research workflows over Maven Bio's drug, trial, company, and deal knowledge graph. Skills for competitive pipelines, indication landscapes, asset profiles, deal and financing activity, and evidence synthesis grounded in FDA, SEC, clinical, and press sources. Requires a Maven Bio account.
16 skills · 1 agent · 1 MCP server
Query the KEGG bioinformatics database — pathways, genes, compounds, drugs, enzymes, diseases, reactions, and more via 34 read-only MCP tools. No API key required.
1 skill · 3 commands · 1 agent · 1 MCP server
Create narrated Mandarin math and science tutorial videos or interactive explainers from problem statements and images.
1 skill
Data Science Team — 10 agents: Cast, Feat, Fit, Score, Drift, Vect, Tune, Plot, Clean, Eval
Automatically nudges Claude to offer learning exercises after git commits. Requires the learning-opportunities plugin.
hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.