ChemDraw Server
Provides chemical informatics endpoints for converting between chemical names and SMILES, processing molecule structures, and comparing molecules, with MCP compatibility.
README
ChemDraw Server
English | 中文
Overview
ChemDraw Server is a unified chemical informatics API service based on FastAPI and FastMCP. It provides endpoints for chemical name/SMILES conversion and molecule structure processing, suitable for integration into chemical drawing tools, automation pipelines, or as a backend for chemical informatics applications.
Features
- Convert chemical names to SMILES strings
- Convert SMILES strings to chemical names
- Convert SMILES to RDKit molecule objects
- MCP compatible API
- API Key (Bearer token) authentication
- Prometheus monitoring integration
- loguru ensemble with uvicorn
Requirements
- Python == 3.10
Installation
git clone https://github.com/tom832/chemdraw-server.git
cd chemdraw-server
uv sync
Usage
Start the server
uv run main_server.py
The API will be available at: http://localhost:1145/chemdraw/api/
The MCP will be available at: http://localhost:1145/chemdraw/mcp/
Need auth
"headers": {
"Authorization": "Bearer <API KEY>"
}
API Endpoints
-
POST /chemdraw/api/name_to_smiles
Convert chemical name to SMILES -
POST /chemdraw/api/smiles_to_name
Convert SMILES to chemical name -
POST /chemdraw/api/smiles_to_rdkit
Convert SMILES to RDKit molecule -
POST /chemdraw/api/mol_compare
Compare two molecule representations using ChemDraw LoadData (auto type detection), return equality (by InChI) and Tanimoto score -
GET /chemdraw/api/health
Health check
API Key
Set your API key in a .env file or via environment variable:
API_KEY=your_api_key_here
DOCS_ACCESS_TOKEN=
Configuration
See config.py for all configurable options.
Dependencies
- fastapi
- fastmcp
- loguru
- mcp[cli]
- prometheus-fastapi-instrumentator
- rdkit
- uvicorn-loguru-integration
License
MIT
中文说明
English | 中文
项目简介
ChemDraw Server 是一个基于 FastAPI 和 FastMCP 的统一化学信息学 API 服务,提供化学名称/SMILES 互转、分子结构处理等接口,适用于集成到化学绘图工具、自动化流程或作为化学信息学应用的后端。
功能特性
- 化学名称转 SMILES
- SMILES 转化学名称
- SMILES 转 RDKit 分子对象
- 兼容 MCP 协议的 API
- API Key (Bearer token) 认证
- 集成 Prometheus 监控
- loguru集成进uvicorn日志
环境要求
- Python == 3.10
安装方法
git clone https://github.com/tom832/chemdraw-server.git
cd chemdraw-server
uv sync
启动服务
uv run main_server.py
API 默认地址为:http://localhost:1145/chemdraw/api/
MCP 地址为:http://localhost:1145/chemdraw/mcp/
需要认证
"headers": {
"Authorization": "Bearer <API KEY>"
}
主要接口
-
POST /chemdraw/api/name_to_smiles
化学名称转 SMILES -
POST /chemdraw/api/smiles_to_name
SMILES 转化学名称 -
POST /chemdraw/api/smiles_to_rdkit
SMILES 转 RDKit 分子对象 -
POST /chemdraw/api/mol_compare
使用 ChemDraw LoadData(不指定类型自动解析)对比两个分子表示,基于 InChI 判等并返回 Tanimoto 分数 -
GET /chemdraw/api/health
健康检查
API Key 配置
在 .env 文件或环境变量中设置:
API_KEY=your_api_key_here
DOCS_ACCESS_TOKEN=
配置项
详见 config.py 文件。
依赖列表
- fastapi
- fastmcp
- loguru
- mcp[cli]
- prometheus-fastapi-instrumentator
- rdkit
- uvicorn-loguru-integration
许可证
MIT
如需进一步完善或定制内容,请告知!
⚠️ Copyright & Disclaimer | 版权与免责声明
English:
ChemDraw, ChemScript and related software are copyrighted by their respective companies. Please ensure you have purchased and are legally using genuine software. This project is for learning and academic reference only, and must not be used for any commercial purpose.
中文:
ChemDraw、ChemScript 等相关软件的版权归其所属公司所有。请确保您已购买并合法使用正版软件。本项目仅供学习与学术参考,不得用于任何商业用途。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.