Skip to main content

novomcp-lite

The lightweight, open-source cheminformatics subset of NovoMCP. Eight zero-config tools — RDKit properties/profiling + public-API search — usable as a Python library or over MCP. Apache-2.0, ~two dependencies, no orchestration core, no services, no keys.

If all you want is the RDKit tool wrappers and a few public-API searches, this is that — nothing heavier.

pip install novomcp-lite
from novomcp_tools import compute_properties, molecule_profile

compute_properties("CC(=O)OC1=CC=CC=C1C(=O)O")
# {'molecular_weight': 180.159, 'logp': 1.31, 'tpsa': 63.6, 'qed': 0.55,
#  'lipinski_pass': True, ...}

molecule_profile("CC(=O)OC1=CC=CC=C1C(=O)O")
# properties + synthetic-accessibility score + RDKit structural alerts

The tools

Tool What it does
calculate_properties MW, logP, TPSA, HBD/HBA, QED, Lipinski — in-process RDKit
get_molecule_info basic properties + a real synthetic-accessibility (SA) score
get_molecule_profile properties + SA + RDKit structural alerts (PAINS/BRENK)
batch_profile profile up to 100 molecules at once
screen_library screen up to 1000 SMILES; optional Lipinski filter
search_chembl ChEMBL compounds / targets / activities (EBI public API)
search_clinical_trials ClinicalTrials.gov v2
search_biorxiv bioRxiv / medRxiv preprints

The five chem tools are fully offline (RDKit only). The three search tools call public APIs — no auth required.

As an MCP server

pip install "novomcp-lite[mcp]"
novomcp-lite            # runs an MCP server over stdio

Point any MCP client (Claude Desktop, an agent, …) at that command and the eight tools appear. The tool logic is identical to the library.

What's intentionally not here

novomcp-lite is the thin, open subset. ADMET prediction, docking, molecular dynamics, quantum chemistry, FAVES compliance, the 122M-molecule index, and the autonomous discovery funnel live in the full NovoMCP engine and its optional compute services. Lite deliberately carries none of that weight — or its dependencies.

Relationship to the full engine

This package is the shared, Apache-2.0 foundation: the full engine builds its orchestration on top of the exact same tool logic you get here. One implementation, two products — so lite's numbers always match the engine's.

Develop

pip install -e ".[dev]"
pytest -q -m "not network"     # offline chem + registry tests
pytest -m network              # live public-API search tests

Contributing

Issues and PRs welcome — API ergonomics, more RDKit-native tools, packaging. Contributions are under Apache-2.0 (DCO sign-off: git commit -s).

License

Apache-2.0 — see LICENSE.

Release files for novomcp-lite 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for novomcp-lite 0.1.1
File Size Uploaded
novomcp_lite-0.1.1.tar.gz 16.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for novomcp-lite 0.1.1
File Interpreter ABI Platform
novomcp_lite-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 36.0 kB

Release files / novomcp_lite-0.1.1.tar.gz

Download URL novomcp_lite-0.1.1.tar.gz
Size 16.8 kB
Tags Source
SHA-256 checksum
How to use checksums
5203898902d9ed310bd8a58b7ba601860776108babe931b3c58fec6359d67bcc
BLAKE2b-256 checksum
How to use checksums
7fd41853b15a38a1dab1bfdd51d80a144ad419238e637c29f686e47db1a5891d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 3, 2026.

Transparency log

Release files / novomcp_lite-0.1.1-py3-none-any.whl

Download URL novomcp_lite-0.1.1-py3-none-any.whl
Size 19.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c7d7fa6de91e93f2e1a80e192b2404220bb7f19738fc7b18d41b7da47fa4ce3c
BLAKE2b-256 checksum
How to use checksums
4ec3aaf2db7aa84ab7ff2be724e54765c0178eb4f2de354c60bd7ca9383ca546
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 3, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page