Metadata-Version: 2.4
Name: sciagentkit
Version: 1.0.3
Summary: MCP-native scientific skills for reproducible computational biology and drug-discovery agents.
Project-URL: Homepage, https://github.com/ehsansyh/sciagentkit
Project-URL: Documentation, https://github.com/ehsansyh/sciagentkit/tree/main/docs
Project-URL: Issues, https://github.com/ehsansyh/sciagentkit/issues
Project-URL: Source, https://github.com/ehsansyh/sciagentkit
Author: Ehsan Sayyah
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agents,cheminformatics,computational-biology,drug-discovery,mcp,openclaw,rdkit,reproducibility,scientific-ai
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Requires-Dist: matplotlib>=3.7.0
Requires-Dist: numpy>=1.23.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: rdkit>=2023.9.1
Requires-Dist: requests>=2.31.0
Requires-Dist: rich>=13.0.0
Requires-Dist: scikit-learn>=1.3.0
Requires-Dist: typer>=0.12.0
Provides-Extra: agent
Requires-Dist: openai-agents>=0.0.15; extra == 'agent'
Provides-Extra: dev
Requires-Dist: build>=1.2.0; extra == 'dev'
Requires-Dist: mypy>=1.10.0; extra == 'dev'
Requires-Dist: pytest>=8.0.0; extra == 'dev'
Requires-Dist: ruff>=0.5.0; extra == 'dev'
Provides-Extra: docking
Requires-Dist: meeko>=0.5.0; extra == 'docking'
Provides-Extra: docs
Requires-Dist: mkdocs-material>=9.5.0; extra == 'docs'
Requires-Dist: mkdocs>=1.6.0; extra == 'docs'
Provides-Extra: forcefields
Requires-Dist: openff-toolkit>=0.16.0; extra == 'forcefields'
Provides-Extra: license
Requires-Dist: cryptography>=42.0.0; extra == 'license'
Provides-Extra: mcp
Requires-Dist: mcp>=1.0.0; extra == 'mcp'
Provides-Extra: md
Requires-Dist: mdanalysis>=2.7.0; extra == 'md'
Requires-Dist: openmm>=8.1.0; extra == 'md'
Requires-Dist: prolif>=2.0.0; extra == 'md'
Provides-Extra: protein
Requires-Dist: biopython>=1.83; extra == 'protein'
Provides-Extra: reports
Requires-Dist: python-docx>=1.1.0; extra == 'reports'
Requires-Dist: reportlab>=4.0.0; extra == 'reports'
Description-Content-Type: text/markdown

<p align="center">
  <img src="https://sciagentkit.com/assets/Sciagentkit_logo.png" alt="SciAgentKit" width="220">
</p>

<p align="center">
  <b>Deterministic scientific tools for AI agents — real computational biology &amp; drug discovery, no invented numbers.</b>
</p>

<p align="center">
  <a href="https://sciagentkit.com">Website</a> ·
  <a href="https://sciagentkit.com/#pricing">Pricing</a> ·
  <a href="https://pypi.org/project/sciagentkit/">PyPI</a> ·
  <a href="mailto:support@sciagentkit.com">Support</a>
</p>

SciAgentKit gives **Claude, Cursor, Gemini CLI and Codex** deterministic tools for drug
discovery — molecule &amp; ADME/tox analysis, target/PDB selection, docking, molecular
dynamics, target-aware hit ranking, wet-lab plans, and signed reports — instead of letting
the model invent descriptors, docking scores, or RMSD values.

> Skills decide the workflow. Deterministic tools run the science. Reports preserve the evidence.

---

## Install

**Full pipeline (recommended)** — one conda environment with every open-source engine
(RDKit, OpenMM, AutoDock Vina, Open Babel, fpocket, …) plus the toolkit:

```bash
curl -O https://sciagentkit.com/environment.yml
conda env create -f environment.yml
conda activate sciagentkit
```

**Analysis only** — pip (molecule/ADME/tox/scaffolds/target selection; no docking/MD):

```bash
pip install "sciagentkit[mcp]"
```

Get your API key at **https://sciagentkit.com** (free 3-day trial), then:

```bash
export SCIAGENTKIT_API_KEY=sak_your_key      # Windows: setx SCIAGENTKIT_API_KEY "sak_..."
```

---

## Use it in your AI agent

**Claude Code**
```bash
claude mcp add sciagentkit -s user \
  --env SCIAGENTKIT_API_KEY=sak_your_key \
  -- python -m sciagentkit.servers.rdkit_server
```

**Cursor / Gemini CLI / Codex**
```bash
sciagent init-agent cursor       # or: gemini | codex | all
```

Then ask your agent naturally:

> *"Dock these ligands against EGFR L858R, rank target-aware top hits, and write a report."*

Full step-by-step guide (all four agents): see **[USER_GUIDE.md](USER_GUIDE.md)** or
[sciagentkit.com](https://sciagentkit.com/#install).

---

## What it does

- **Molecule libraries** — canonicalization, descriptors (MW, logP, QED, TPSA), scaffold diversity, novelty audits (RDKit)
- **ADME &amp; toxicity** — ESOL solubility, drug-likeness (Lipinski/Veber/Ghose/Egan), GI/BBB heuristics, PAINS/Brenk alerts
- **Targets** — UniProt resolution + mutation-aware PDB ranking
- **Docking** — pocket detection (crystal-ligand / fpocket / P2Rank) + Vina/GNINA/smina, ranked poses
- **Molecular dynamics** — OpenMM setup + trajectory RMSD/RMSF + ProLIF interactions
- **Target-aware hit ranking** — combines docking, MD stability, and ADME/tox (toxicity penalized; BBB up-weighted for CNS targets)
- **Wet-lab validation plans** — staged assays + recommended cell lines for the target
- **Signed, reproducible reports** — Markdown / PDF / DOCX with a `run_manifest.json` (input hashes + tool versions)

Every value is computed by real tools, never inferred by a language model. Outputs are saved
under `runs/` with a reproducibility manifest.

---

## Free vs paid

| | Trial (3 days) | Individual / Team |
|---|---|---|
| Molecule analysis, ADME/tox, target selection | ✅ | ✅ |
| Docking | 1 run | ✅ unlimited |
| Molecular dynamics | ❌ | ✅ |
| Hit ranking, wet-lab plans, reports | ✅ | ✅ |
| Expert review of results | — | add-on |

Team plans are per seat. Manage your plan at [sciagentkit.com](https://sciagentkit.com).

---

## Scientific limits

SciAgentKit is a workflow and tooling layer, not expert review. Docking scores are ranking
heuristics, not binding free energies; short MD validates setup and analysis plumbing, not
equilibrium stability. Receptor protonation, missing loops, cofactors, metals, membrane
context, and ligand parameterization still require expert review.

---

## Support

Account, docs, and billing: **https://sciagentkit.com** — questions: **support@sciagentkit.com**

© 2026 Istanbulmedchem. All rights reserved.
