Atlas / MCP servers / sebotic / CDK Pywrapper

CDK PywrapperCAUTION

Name: CDK Pywrapper
Author: sebotic

mcp/sebotic/cdk-pywrapper

MCP server by sebotic · cdk · chemistry · chemistry development kit · Audited 2026-10-08

⚑ Report / re-scan Source ↗

A Python wrapper for the Chemistry Development Kit (CDK)

Verdict

CAUTION

Grade

Trust score

87 /100

Exposed tools

8 8r · 0w · 0d

Transport

—

License

AGPL-3.0

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Python Wrapper for the Chemistry Development kit

tl;dr

A Python wrapper for the Chemistry Development Kit (CDK), which is written in Java
Primary purpose:
Generate diverse chemical compound identifiers (SMILES, InChI).
Inter-convert between these identifiers.
Integration with chem
Fully compatible with Python 3.x.

Motivation

Cheminformatics only has a small number of open source tools, e.g. OpenBabel, the Chemistry Development Kit and RDKit.

Every framework has its pros and cons, e.g. OpenBabel has issues with InChI generation from SMILES.

CDK lacks the ability to be used with Python, while Python has become the indispensable programming language for data science, also in cheminformatics and computational biology.

Also, all three frameworks lack integration with databases.

Installation

Before installing cdk_pywrapper, make sure to have a Java JDK available on your system, e.g. OpenJDK.

Then, you can install from the repository directly.

# Create Python virtual environment named 'cdk_pywrapper'
python3 -m venv ./cdk_pywrapper
source ./cdk_pywrapper/bin/activate

# Clone repository from GitHub
git clone https://github.com/sebotic/cdk_pywrapper.git
cd cdk_pywrapper

# Install into created venv
pip install .

This will install the package on your local system. Setuptools will take care of downloading the CDK.jar and it will build the cdkbridge.java. So after that, cdkpywrapper should be ready to use, like in the example below.

cdk_pywrapper was tested on Linux and MacOS, but it should also work on Windows.

Example

from cdk_pywrapper.cdk_pywrapper import Compound

smiles = 'CCN1C2=CC=CC=C2SC1=CC=CC=CC3=[N+](C4=CC=CC=C4S3)CC.[I-]'
cmpnd = Compound(compound_string=smiles, identifier_type='smiles')
ikey = cmpnd.get_inchi_key()
print(ikey)

Output: 'MNQDKWZEUULFPX-UHFFFAOYSA-M'

MCP server

I al

Read from source at commit 224922749a82OBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add cdk_pywrapper -- uvx cdk_pywrapper

claude-desktop

{
  "mcpServers": {
    "cdk_pywrapper": {
      "command": "uvx",
      "args": [
        "cdk_pywrapper"
      ]
    }
  }
}

Exposed tools (8)

8 read · 0 write · 0 destructive.

Tool	Risk	Description
`calculate_lipinski_rule_of_5`	read
`calculate_molecular_descriptors`	read
`generate_molecule_svg`	read
`get_compound_identifiers`	read
`get_tautomers`	read
`perform_substructure_search`	read
`query_chembl_by_inchi_key`	read
`search_compound_by_name`	read

Trust audit

CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	WARN
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED