Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add qfoldit/Protein-Design-MCP --skill bionemo-agent-toolkitgit clone --depth 1 https://github.com/qfoldit/Protein-Design-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qfoldit/protein-design-mcp/bionemo-agent-toolkit)<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/bionemo-agent-toolkit"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/bionemo-agent-toolkit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/bionemo-agent-toolkit"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/bionemo-agent-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00159 | $0.01675 |
| Opus 5 | $0.00079 | $0.00838 |
| Sonnet 5 | $0.00032 | $0.00335 |
| Haiku 4.5 | $0.00016 | $0.00168 |
Grade A, and why
qfoldit-bionemo-agent-toolkit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qFoldIT BioNeMo Agent Toolkit
A client for five NVIDIA BioNeMo NIM microservices that do not already have
their own MCP server, plus documented guidance on the one that does
(AlphaFold3, via alphafold3_mcp).
Read references/api_reference.md before answering — exact endpoint
paths and request/response shapes, each individually verified against
NVIDIA's own documentation. Read references/alphafold3_mcp.md before
saying anything about AlphaFold3 specifically — the integration approach
there was corrected this session (see below).
What is implemented
| Component | Function | Requirement |
|---|---|---|
| AlphaFold2 | predict_protein_structure_af2(sequence, ...) |
Self-hosted NIM container, NGC API key |
| DiffDock | dock_ligand(protein_pdb, ligand, ...) |
Self-hosted NIM container, NGC API key |
| MolMIM | generate_molecules(seed_smiles, ...), get_molecule_embedding(smiles) |
Self-hosted NIM container, NGC API key |
| Evo 2 | generate_dna_sequence_evo2(sequence, ...) |
Self-hosted NIM container, H100/H200-class GPU |
| Boltz-2 | predict_structure_boltz2(polymers, ligands=..., ...) |
Self-hosted NIM container, >=48GB VRAM GPU |
All five are implemented in scripts/bionemo_client.py as thin, honest
requests-based HTTP clients against a self-hosted NIM container
(default base_url="http://localhost:8000"). Every endpoint/payload shape
was checked against NVIDIA's own docs during this session — see
references/api_reference.md for citations per model. On any HTTP
failure, the real error (status + body) is raised; no result is ever
fabricated.
AlphaFold3 — different pattern, not reimplemented here
AlphaFold3 is not wrapped by this skill's own code. It already has a
separate, real MCP server — MacromNex/alphafold3_mcp
— which should be installed and connected in the same Claude session, the
same way qFoldIT treats unity-mcp, UnrealClaude, or kit-usd-agents
elsewhere: when an existing bridge already covers a tool, use it
directly instead of duplicating it. See references/alphafold3_mcp.md
for what was (and was not) verified about it this session — in
particular, its exact exposed tool names were not confirmed; introspect
the connected server's tool list rather than assuming names.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 127 lines · 159 tokens per session scan A 1f13ab5e9ccd
qfoldit-bionemo-agent-toolkit is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 159 tokens to every session and 1,675 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.