# RDKit Chemical Informatics Server

> Use this tool when you need to perform advanced chemical informatics tasks, such as molecular visualization, descriptor calculation, and interaction with a Model Context Protocol (MCP) server. It takes molecular inputs and generates images, calculates descriptors like molecular weight and logP, and communicates with an MCP server for further analysis. Ideal for use cases requiring chemical analysis and visualization, with a Python-based interface and output in formats like images and molecular descriptors.

Canonical page: https://skillsregistry.net/skills/s20ss-mcp-rdkit  
JSON: https://api.skillsregistry.net/v1/skills/s20ss-mcp-rdkit

## Description

# MCP RDKit Project

## Overview

The `mcp_rdkit` project integrates the RDKit library with the MCP (Model Context Protocol) framework to provide advanced chemical informatics tools. It includes functionalities for molecular visualization, descriptor calculation, and interaction with an MCP server.

## Features

- **Molecular Visualization**: Generate images of molecules using RDKit.
- **Descriptor Calculation**: Compute molecular descriptors such as molecular weight, logP, and more.
- **MCP Server Integration**: Communicate with an MCP server for advanced chemical informatics tasks.

## Project Structure

- `mcp_rdkit/`
  - `__main__.py`: Entry point for the application. It initializes the MCP server and runs it in "stdio" mode.
  - `rdkit_helper.py`: Contains helper functions for RDKit operations, including:
    - Converting PIL images to base64.
    - Interfacing with the MCP server.
    - Utilizing RDKit for chemical computations.



- `setup.py`: Configuration for packaging and distribution.

## Requirements

- Python 3.8 or higher
- RDKit library
- MCP framework

## Installation

1. Install the package using pip:
   ```bash
   pip install mcp-rdkit
   ```

2. Run the application:
   ```bash
   python -m mcp_rdkit
   ```

## Demo

You can integrate this directly into Claude App:

![Demo 1](uploads/image.png)
![Demo 2](uploads/image%20(1).png)
![Demo 3](uploads/image%20(2).png)


## Usage

- **Run the MCP server**:
  The application starts an MCP server that can process chemical informatics tasks.

- **Generate molecular images**:
  Use the RDKit helper functions to visualize molecules.

- **Calculate descriptors**:
  Leverage RDKit's descriptor calculation tools for chemical analysis.

## MCP Configuration Example

To use the RDKit server with MCP, add the following configuration to your `mcp` config file:

```json
"rdkit-server": {
  "type": "stdio",
  "command": "python",
  "args": [
    "-m",
    "mcp_rdkit"
  ]
}
```

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/s20ss/mcp_rdkit)
- **Repository:** <https://github.com/s20ss/mcp_rdkit>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "s20ss-mcp-rdkit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/s20ss-mcp-rdkit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/s20ss-mcp-rdkit/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt