RDKit Chemistry
MCP server that enables language models to interact with RDKit through natural language
What is RDKit Chemistry?
RDKit Chemistry is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables language models to interact with rdkit through natural language
MCP server that enables language models to interact with RDKit through natural language
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server that enables language models to interact with RDK
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx rdkitConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use RDKit Chemistry
The RDKit MCP Server exposes RDKit's cheminformatics functions to any MCP-compatible language model through natural language, covering the full RDKit 2025.3.1 API without requiring the user to write code. Researchers in drug discovery, cheminformatics, and molecular analysis can ask questions about SMILES strings, compute molecular properties, generate fingerprints, perform substructure searches, and more — all conversationally. It is built by TandemAI and is designed for agent-level, code-free access to a mature scientific computing library.
Prerequisites
- Python 3.8 or higher installed
- RDKit installed (conda install -c conda-forge rdkit or pip install rdkit)
- The rdkit-mcp-server repository cloned locally
- An MCP-compatible client such as Claude Desktop
- Optionally an OpenAI API key if using the built-in CLI client
Clone the repository and install dependencies
Clone the rdkit-mcp-server repository and install it with pip. RDKit must already be available in your Python environment.
git clone https://github.com/tandemai-inc/rdkit-mcp-server.git
cd rdkit-mcp-server
pip install .Review available settings
Copy the example settings file to configure which RDKit tools are exposed and any server options.
cp settings.example.yaml settings.yaml
# Edit settings.yaml as neededStart the MCP server
Run the server script. By default it listens for MCP connections and exposes the full set of RDKit tools.
python run_server.py --settings settings.yamlList available tools (optional)
Use the list_tools script to see all RDKit functions exposed by the server before connecting your AI client.
python list_tools.py --settings settings.yamlAdd the server to your MCP client configuration
Register the server in your Claude Desktop config or equivalent MCP client so the AI can call RDKit tools.
{
"mcpServers": {
"rdkit": {
"command": "python",
"args": ["/path/to/rdkit-mcp-server/run_server.py", "--settings", "/path/to/rdkit-mcp-server/settings.yaml"]
}
}
}RDKit Chemistry Examples
Client configuration
Claude Desktop configuration for the RDKit MCP server using the run_server.py entry point.
{
"mcpServers": {
"rdkit": {
"command": "python",
"args": [
"/home/user/rdkit-mcp-server/run_server.py",
"--settings",
"/home/user/rdkit-mcp-server/settings.yaml"
]
}
}
}Prompts to try
Ask RDKit questions in natural language once the server is connected to your MCP client.
- "What is the molecular weight of aspirin? Its SMILES is CC(=O)Oc1ccccc1C(=O)O"
- "Generate a Morgan fingerprint with radius 2 for caffeine (SMILES: Cn1cnc2c1c(=O)n(c(=O)n2C)C)"
- "Does the molecule CC(=O)Nc1ccc(O)cc1 contain a phenol substructure?"
- "Calculate the LogP and TPSA for ibuprofen: CC(C)Cc1ccc(cc1)C(C)C(=O)O"
- "Find the Murcko scaffold for the molecule C1CCN(CC1)c1ncnc2[nH]cnc12"Troubleshooting RDKit Chemistry
ImportError: No module named 'rdkit'
RDKit must be installed separately before installing the server. Use conda: `conda install -c conda-forge rdkit`, or pip: `pip install rdkit`. Confirm with `python -c 'from rdkit import Chem; print(Chem.__version__)'`.
Server starts but no tools appear in the MCP client
Check the settings.yaml to ensure tools are not disabled. Restart the MCP client after updating the config. Run `python list_tools.py` to confirm the server itself is exposing tools.
Invalid SMILES errors when querying molecules
RDKit will return an error for malformed SMILES strings. Validate your SMILES input using a tool like https://www.cheminfo.org/Chemistry_-_Cheminformatics/Mole_cule/SMILES_validator/ before passing it to the server.
Frequently Asked Questions about RDKit Chemistry
What is RDKit Chemistry?
RDKit Chemistry is a Model Context Protocol (MCP) server that mcp server that enables language models to interact with rdkit through natural language It connects AI assistants to external tools and data sources through a standardized interface.
How do I install RDKit Chemistry?
Follow the installation instructions on the RDKit Chemistry GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with RDKit Chemistry?
RDKit Chemistry works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is RDKit Chemistry free to use?
Yes, RDKit Chemistry is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
RDKit Chemistry Alternatives — Similar Data Science & ML Servers
Looking for alternatives to RDKit Chemistry? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架,结合 MCP Skills 多智能体协作架构,实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up RDKit Chemistry in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use RDKit Chemistry?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.