ChemMCP
About
A collection of 19 professional tools for chemical molecular processing based on the Model Context Protocol (MCP).
Details
- Author
- cassiusoat
- Categories
- Developer Tools, Other
Jump to
Setup
Install ChemMCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/cassiusoat/ChemMCP_lite
Follow the installation instructions in the repository README, then restart your MCP client.
ChemMCP是一个基于模型上下文协议(MCP)的化学分子计算工具集合,提供19个专业的化学分子处理工具。
- Python 3.11+ (推荐Python 3.11或3.12)
- Conda 环境管理器
conda create -n chemmcp python=3.11 conda activate chemmcp
# 安装核心依赖,支持17个工具 pip install -r requirements.txt
支持的工具: 除MoleculeCaptioner和MoleculeGenerator外的所有工具
# 方式A: 使用可选依赖组 pip install -e ".[ai]" # 方式B: 手动安装AI依赖 pip install -r requirements.txt pip install transformers>=4.20.0 torch>=1.9.0
# 安装所有依赖和开发工具 pip install -e ".[all,dev]"
# 网络搜索工具所需(必需) export TAVILY_API_KEY="your_tavily_api_key" # LLM工具所需(必需) export LLM_MODEL_NAME="openai/gpt-4o" export OPENAI_API_KEY="your_openai_api_key" # ChemSpace工具所需(可选,仅在PubChem查找失败时作为后备) export CHEMSPACE_API_KEY="your_chemspace_api_key"
功能: 执行网络搜索以获取化学相关信息输入: 搜索查询字符串输出: 搜索结果和相关链接
功能: 计算分子的分子量输入: SMILES分子结构字符串输出: 分子量数值
功能: 统计分子中各种原子的数量输入: SMILES分子结构字符串输出: 各原子类型的数量统计
功能: 计算两个分子的Tanimoto相似度输入: 两个SMILES分子结构字符串输出: 相似度分数(0-1)
功能: 识别分子中存在的官能团输入: SMILES分子结构字符串输出: 检测到的官能团列表
功能: 将SMILES字符串转换为标准化形式输入: SMILES分子结构字符串输出: 标准化的SMILES字符串
功能: 将IUPAC化学名称转换为SMILES格式输入: IUPAC化学名称输出: 对应的SMILES字符串
功能: 将SMILES格式转换为IUPAC化学名称输入: SMILES分子结构字符串输出: 对应的IUPAC化学名称
功能: 将SMILES格式转换为分子式输入: SMILES分子结构字符串输出: 分子式(如C2H6O)
功能: 将化学物质的通用名称转换为SMILES格式输入: 化学物质名称输出: 对应的SMILES字符串
功能: 将SELFIES格式转换为SMILES格式输入: SELFIES字符串输出: 对应的SMILES字符串
功能: 将SMILES格式转换为SELFIES格式输入: SMILES分子结构字符串输出: 对应的SELFIES字符串
功能: 将SMILES格式转换为CAS登记号输入: SMILES分子结构字符串输出: 对应的CAS登记号
功能: 验证SMILES字符串的语法正确性输入: SMILES分子结构字符串输出: 验证结果(有效/无效)
功能: 验证反应SMILES字符串的语法正确性输入: 反应SMILES字符串输出: 验证结果(有效/无效)
功能: 生成分子的2D结构图输入: SMILES分子结构字符串输出: 分子结构图像
功能: 使用AI生成分子的文字描述输入: SMILES分子结构字符串输出: 分子的详细文字描述
功能: 使用AI根据描述生成分子结构输入: 分子描述文本输出: 对应的SMILES分子结构
功能: 对分子进行化学修饰和衍生化输入: SMILES分子结构字符串输出: 修饰后的分子结构选项
# 启动MCP服务器,使用特定工具 python -m chemmcp --tools WebSearch MoleculeWeight MoleculeAtomCount # 或使用所有工具 python -m chemmcp --tools WebSearch MoleculeWeight MoleculeAtomCount MoleculeSimilarity FunctionalGroups SmilesCanonicalization Iupac2Smiles Smiles2Iupac Smiles2Formula Name2Smiles Selfies2Smiles Smiles2Selfies Smiles2Cas MoleculeSmilesCheck ReactionSmilesCheck MoleculeVisualizer MoleculeCaptioner MoleculeGenerator MoleculeModifier
{ "mcpServers": { "ChemMCP": { "command": "/opt/miniconda3/envs/chemmcp/bin/python", // 如何找到路径: conda activate chemmcp && which python "args": [ "-m", "chemmcp", "--tools", "WebSearch", "MoleculeWeight", "MoleculeAtomCount", "MoleculeSimilarity", "FunctionalGroups", "SmilesCanonicalization", "Iupac2Smiles", "Smiles2Iupac", "Smiles2Formula", "Name2Smiles", "Selfies2Smiles", "Smiles2Selfies", "Smiles2Cas", "MoleculeSmilesCheck", "ReactionSmilesCheck", "MoleculeVisualizer", "MoleculeCaptioner", "MoleculeGenerator", "MoleculeModifier" ], "toolCallTimeoutMillis": 300000, "env": { "TAVILY_API_KEY": "your_tavily_api_key_here", "LLM_MODEL_NAME": "openai/gpt-4o", "OPENAI_API_KEY": "your_openai_api_key_here", "CHEMSPACE_API_KEY": "your_chemspace_api_key_here", // 可选:仅在需要额外数据库查找时使用 "PATH": "/opt/miniconda3/envs/chemmcp/bin:/usr/local/bin:/usr/bin:/bin" // 如何找到路径: conda activate chemmcp && echo $PATH } } } }
- 如何找到正确的Python路径:
# 激活您的conda环境 conda activate chemmcp # 查看Python路径 which python # 复制输出的路径并替换上面配置中的路径
- RDKit: 分子处理和计算的核心库
- PubChemPy: PubChem数据库接口
- SELFIES: 分子的自引用嵌入式字符串表示
- rdchiral: 手性分子处理
- synspace: 分子空间探索和修饰
- tavily-python: 网络搜索API
- litellm: 统一的LLM API接口
- requests: HTTP请求库
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Search 3,500+ US universities, estimate admission chances, check financial aid by income bracket, and build balanced college lists. Free MCP server, no API key required. Data from IPEDS and College Scorecard
Provides astronomical data such as celestial object positions, rise/set times, and visibility information.
The Ultimate Math Engine - Unifying SymPy, NumPy & Matplotlib in one powerful server! Perfect for devs & researchers.
Provides seamless access to particle physics data from the Particle Data Group (PDG) for AI assistants and applications.
Calculate permeability of porous media using the seepage distance method, derived from the Darcy's law-based formula
UK property data: crime stats, schools, demographics, valuations, comparables, Ofsted ratings
MCP server for symbolic math derivation, calculation, and verification
A high-performance Model Context Protocol (MCP) server for math-ing whilst vibing with LLMs. Built with Polars, Pandas, NumPy, SciPy, and SymPy for optimal calculation speed and comprehensive mathematical capabilities from basic arithmetic to advanced calculus and linear algebra.
Access Wolfram Alpha's computational knowledge engine for expert-level answers and data analysis.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





