tamarind
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-so
npx skills add K-Dense-AI/scientific-agent-skills --skill tamarind --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Tamarind provides access to a collection of open-source molecular design and structural biology tools through a cloud platform, via its REST API or MCP server. It supports structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein and binder design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein–ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. It handles batch submissions and pipelines, operating in the cloud without local GPUs.
How it works
The skill guides the agent to:
- Sign in to Tamarind Bio and obtain an API key from app.tamarind.bio, then pass it in the x-api-key header.
- Discover available tools via the REST endpoint /tools or the MCP equivalents, and select tools by name (e.g., alphafold).
- Retrieve each tool’s exact settings schema (REST includes an inline schema per tool; MCP can return a full getJobSchema for the tool).
- Validate a candidate job using validateJob (MCP) before submission to catch missing/invalid fields.
- Submit a job with a settings dictionary matching the tool’s schema via submit-job (REST) or submitJob (MCP).
- Poll job status with GET /jobs and retrieve results via POST /result, following the two-step result retrieval process (presigned URL retrieval then download).
- Use MCP endpoints such as getJobs, getResult, listJobFiles, and uploadFile as needed for agent-host workflows.
- Use MCP to reason about gating keys and defaults; for inputs, sequences may be multi-chain (use a colon to separate chains).
When to use it
Use Tamarind when you want to run open-source structure prediction, design, docking, affinity, MSA, or MD workflows in the cloud rather than on local hardware. It is suitable for batch screening and pipeline chaining where tool discovery and parameter schemas are dynamic.
What it can touch
The REST API and MCP surface these endpoints and capabilities: /tools, /submit-job, /jobs, /result, /upload, /files, and MCP methods like listModalities, getAvailableTools, getJobSchema, validateJob, submitJob, getJobs, getJobLogs, listJobFiles, getResult, uploadFile. Authentication uses the x-api-key header, with TAMARIND_API_KEY as the environment variable.
Caveats
Requires Python 3.10+ context for client code and an active Tamarind Bio account with an API key from app.tamarind.bio. Network access is required to reach the REST API or MCP server; there is no official Python SDK. Pricing includes a baseline of 10 free jobs per user; further usage requires a subscription.
# Tamarind Bio Tamarind Bio is a cloud platform that runs computational biology tools — structure prediction, protein and antibody design, docking, binding-affinity, MSA generation, and molecular dynamics — on managed GPUs. Users submit sequences or structures and get back predicted structures, designs, and biophysical scores, without provisioning their own hardware. It exposes hundreds of tools (AlphaFold, Boltz-2, Chai-1, RFdiffusion, ProteinMPNN, BoltzGen, ESMFold2, DiffDock, Autodock Vina, and many more) through one uniform job API. **Official docs:** [app.tamarind.bio/api-docs](https://app.tamarind.bio/api-docs) · platform UI at [app.tamarind.bio](https://app.tamarind.bio) ## Canonical sources — fetch these, don't rely on a stale copy Tamarind publishes live, machine-readable sources. Prefer fetching them at runtime over trusting any hardcoded list — tool names, schemas, and endpoints change frequently: - **`https://app.tamarind.bio/llms.txt`** — LLM index: links to the spec, API docs, and MCP guide. - **`https://app.tamarind.bio/openapi.yaml`** — OpenAPI 3.0 spec for the 8 core job endpoints (submit-job/-batch, jobs, result, upload, files, delete-job/-file; auth `ApiKeyAuth`)
- Canonical sources — fetch these, don't rely on a stale copy
- When to use this skill
- Access and authentication
- Two ways to call Tamarind
- MCP server (best for AI agents)
- REST API (universal)
- Core workflow
- Discovering tools
- Choosing the right tool
- Job settings, schemas, and validation
- File inputs (PDB, CIF, SDF, …)
- Chaining jobs into pipelines
- Batch submission
- Job status lifecycle
export TAMARIND_API_KEY="your_api_key" List available tools curl https://app.tamarind.bio/api/tools \
What does the tamarind skill do?
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-so
How do I install it?
Run `npx skills add K-Dense-AI/scientific-agent-skills --skill tamarind --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From K-Dense-AI/scientific-agent-skills, a repository with 32,619 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.