What are the prerequisites for the server machine?
Python 3.x, git, `uv` (Python project manager), and `wgrib2` installed and accessible in the system’s PATH are required. Also, an MCP Client environment must be able to connect to this server.
@yskmasumoto
基本信息
An MCP server for executing wgrib2 commands from MCP Client. Designed with a simple approach where converted files are saved to a specific folder.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"wgrib2-easy-mcp": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A simple MCP server designed to execute wgrib2 commands remotely via an MCP Client. Processed files are saved to a designated output directory. It is intended for users who need to interact with GRIB2 meteorological data files through a remote client interface.
Clone the repository, install dependencies with uv pip install -r requirements.txt, and configure environment variables—notably the required OUTPUT_DIR (must exist before starting). Start the server with uv run --with python-dotenv --with mcp src/server.py. Connect your MCP Client and invoke the available tools, providing the path to a GRIB2 file. A sample script (src/sample/sample.py) demonstrates usage patterns.
Python 3.x, git, `uv` (Python project manager), and `wgrib2` installed and accessible in the system’s PATH are required. Also, an MCP Client environment must be able to connect to this server.
Set the environment variable `OUTPUT_DIR` to an absolute path (the directory must exist before starting the server). Optionally set `WGRIB2_PATH` (defaults to `wgrib2` in PATH) and `TEST_GRIB2_FILE` for the sample script.
Three stable MCP tools: `list_contents` (lists inventory), `show_details` (displays message details), and `show_help` (provides wgrib2 help documentation).
No. Element extraction and conversions to CSV/binary are currently under development and are only demonstrated in the sample script for illustration. Stable tools for these operations are not yet provided.
All generated files (e.g., CSV, binary extracts) are saved directly into the directory specified by the `OUTPUT_DIR` environment variable on the server machine. This directory must exist before launching the server.

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected

Model Context Protocol Servers
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.
MCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
MCP server to extract contents from a PDF file
评论