SWMM-MCP
An MCP server that provides a toolbox for interacting with EPA SWMM stormwater models, enabling users to analyze model data and interpret results through LLM-driven tools. It assists stormwater modelers in understanding hydraulic systems and modeling behavior using natural language interfaces.
README
SWMM-MCP
MCP Toolbox for SWMM
Setup
- Install uv
- Clone this repository
- Install dependencies with:
uv sync
Usage
Put the following json block into an MCP client (e.g. Claude Desktop).
If you are currently in the root folder of this project in your IDE, you can find your full directory path by entering the command pwd.
{
"mcpServers": {
"SWMM": {
"command": "uv",
"args": [
"run",
"--directory",
"/<path/to/directory>/SWMM-MCP",
"server.py"
]
}
}
}
On windows it might look something like this:
{
"mcpServers": {
"SWMM": {
"command": "uv",
"args": [
"run",
"--directory",
"C:\\path\\to\\directory\\SWMM-MCP",
"server.py"
]
}
}
}
If your client lets you use a system prompt, this has been working somewhat well.
You are an expert stormwater modeler specializing in EPA SWMM. You must use available tools to help users understand their
models and interpret results. When the user asks a question, first identify which tools would be most helpful before proceeding.
Explain technical terms and provide context for results.
Be friendly, helpful, and concise. End responses with 2-3 specific follow-up suggestions based on the analysis.
Development
To test a tool without actually using an LLM, you can use the utility in test.py. Specify the following variables and run it either through an IDE, or with uv run test.py.
# server.py : function to test
@mcp.tool()
def model_info(model_name):
pass
# in test.py:
tool_name = "model_info"
tool_parameters = {
"model_name": "base_model"
}
To add a new python package, use the command:
uv add <package name>
This will take care of updating pyproject.toml and the lock file, keeping all of our environments on the same page.
Troubleshooting
Adding server to client failure
For mac users, you may run into an issue of the client being unable to find the path uv is installed. To resolve this issue, you can create a symlink to one of the paths the client already checks.
To first find where uv is installed, in your terminal run:
which uv
which will return something like:
/Users/<user-name>/.local/bin/uv
Then, to create a symlink, in your terminal run:
sudo ln -s ~/.local/bin/uv /usr/local/bin/uv
where ~/.local/bin/uv is where uv is installed and /usr/local/bin/uv is part of the path your client checks. The error logs from the client should contain the paths it checks for uv.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。