About MCP Cooking Units Converter
MCP Cooking Units Converter is a Python package and MCP server for cooking measurements. It provides conversion tools for volume, weight, and temperature for MCP-compatible tools and VSCode extensions.
Key features
- 01Volume unit conversion
- 02Weight unit conversion
- 03Temperature conversion
- 04Python package and MCP server
Use cases
- 01Convert recipe volumes between common units
- 02Convert ingredient weights for a recipe
- 03Convert oven temperatures between Celsius and Fahrenheit
MCP support
Exposes volume, weight, and temperature conversion tools to MCP-compatible clients and extensions.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Cooking Units Converter
MCP Cooking Units Converter is a Python package and MCP server for converting cooking measurements (volume, weight, temperature) between common units. It is designed for integration with MCP-compatible tools and VSCode extensions.
Installation
Installing via Smithery
To install Cooking Units Converter for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @sellisd/mcp-units --client claude
Manual Installation
- Clone the repository:
git clone [email protected]:sellisd/mcp-units.git
cd mcp-units
- Install:
uv pip install . # For normal use
# OR
uv pip install -e . # For development
Usage
Available Tools
The server provides the following conversion tools:
-
Volume Conversion
- Convert between: ml, l, cup, tbsp, tsp
- Example: 240ml → 1 cup
-
Weight Conversion
- Convert between: g, kg, oz, lb
- Example: 454g → 1 lb
-
Temperature Conversion
- Convert between: Celsius (C), Fahrenheit (F)
- Example: 180°C → 356°F
Running the Server
uvx --with . python -m mcp_units.server
Using with VSCode Extensions
This MCP server can be integrated with VSCode extensions that support the Model Context Protocol. Here's how to set it up:
-
Install an MCP-compatible VSCode extension (e.g., Roo)
-
Configure the extension to use this server in
.roo/mcp.json:{ "mcpServers": { "units": { "command": "uvx", "args": [ "--with", ".", "python", "-m", "mcp_units.server" ], "disabled": false } } }
Contact
For questions, issues, or contributions, please visit the GitHub repository.
License
This project is licensed under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.