Tamarind Bio Cloud Molecular Design API
Run open-source structural biology and molecular design tools (AlphaFold, Boltz, RFdiffusion, DiffDock…) on Tamarind Bio's managed GPUs via its REST API or MCP server.
Web & APIAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026
What it does
Teaches Claude to drive the Tamarind Bio platform end to end so computational biology jobs run on managed cloud GPUs instead of local hardware.
- Enforces the canonical loop: discover tools → fetch schema → validate → submit → poll → retrieve results.
- Covers structure prediction (AlphaFold, Boltz-2, Chai-1, ESMFold2), protein/binder/de novo design (RFdiffusion, ProteinMPNN, LigandMPNN, BoltzGen, BindCraft), antibody & nanobody design and developability, docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics.
- Supports both REST (
x-api-keyheader) and the hosted MCP server (mcp.tamarind.bio/mcp), withvalidateJobdry-runs before submission. - Documents the non-obvious behaviors:
GET /jobs?jobName=returns a bare row,/resultis a two-step presigned download, batch parents poll onbatchStatus(not subjob status), uploaded files are referenced by bare filename, and file-typed params treat plain strings as inline content.
Who it's for
- Researchers and biotech engineers without local GPU capacity
- Teams batch-screening dozens to hundreds of sequences through one tool
- Anyone chaining design → fold → score into pipelines
- (Prerequisites) A Tamarind Bio account and API key, Python 3.10+, network access. Only 10 free jobs; beyond that a paid subscription is required.
Examples
- "Fold this sequence with AlphaFold" → pull the tool schema, submit the job, poll every 30s, download the results zip.
- "Verify every sequence my ProteinMPNN run designed" → MCP
submitBatch(fromJob="my-proteinmpnn-job", type="alphafold"), then wait for the parent'sbatchStatusto hit Complete. - "Dock this ligand set into my target PDB pocket" → upload the receptor, reference it by bare filename, compare
autodock-vinavs.boltzco-folding, then submit as a batch.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/tamarind/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/tamarind folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/tamarind/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/tamarind ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the skill in:
cp -r scientific-agent-skills/skills/tamarind ~/.claude/skills/ - Sign in at app.tamarind.bio and create an API key in your account/API settings.
- Export the key:
export TAMARIND_API_KEY="your_api_key"(add it to~/.zshrcor~/.bashrcto persist). - Verify access:
curl https://app.tamarind.bio/api/tools -H "x-api-key: $TAMARIND_API_KEY" - Restart Claude Code, then ask something like "use Tamarind to fold this sequence" to trigger the skill.
View source on GitHub ↗License: MIT