About Bowlly
Bowlly is an MCP server for finding and evaluating cat food, intended for use with Claude Desktop. It combines product search, nutrition analysis, and side-by-side comparisons.
Key features
- 01Search by ingredients, conditions, and form
- 02View product details and ingredients
- 03Compare products side by side
- 04Analyze ingredients and carbohydrates
- 05Browse curated category recommendations
Use cases
- 01Find dry food without grains
- 02Check food for a cat with a sensitive stomach
- 03Review a product’s nutrition
- 04Compare two cat food products
MCP support
Bowlly exposes five cat food search and analysis tools to MCP clients, including Claude Desktop. It supports product lookup, nutrition analysis, comparisons, and curated lists.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMEBowlly MCP Server
MCP (Model Context Protocol) server for Bowlly cat food product search and ingredient analysis. Enables Claude Desktop to search, analyze, and compare cat food products.
Prerequisites
- Node.js 22+ - Required for running the MCP server
- Claude Desktop - Download here if not installed
Quick Start
Option 1: One-Command Setup (Recommended)
npx @bowlly/mcp-server --setup
After running, restart Claude Desktop and you're ready to go!
Option 2: Manual Configuration
-
Edit your Claude Desktop config at the appropriate path for your OS:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- macOS:
-
Add the Bowlly server configuration:
{
"mcpServers": {
"bowlly": {
"command": "npx",
"args": ["-y", "@bowlly/mcp-server"]
}
}
}
- Save the file and restart Claude Desktop
Available Tools
| Tool | Description |
|---|---|
search_products | Search by ingredients, conditions, form |
get_product_detail | Full product info with ingredients |
compare_products | Side-by-side comparison |
analyze_nutrition | Ingredient breakdown & carb analysis |
get_curation_list | Best-of category recommendations |
Example Natural Language Queries
"Find grain-free dry cat foods"
"Show me wet foods without chicken"
"Analyze the nutrition of Blue Buffalo Wilderness"
"Compare Orijen and Acana cat foods"
"What are the best low-carb options?"
"Show me foods for cats with sensitive stomachs"
Configuration
Config File Locations by Platform
| Platform | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%/Claude/claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Verification
To confirm the MCP server is working:
- Restart Claude Desktop (required after configuration changes)
- Open the tools menu - Look for the hammer icon in the bottom left
- Verify Bowlly tools appear - You should see 5 tools listed
- Test with a query: Try asking "Find grain-free dry cat foods"
Troubleshooting
Tools not showing in Claude?
- Restart Claude Desktop - Configuration changes require a restart
- Check the config file path - Ensure you're editing the correct file for your OS
- Verify JSON syntax - Use a JSON validator if unsure
- Check Claude Desktop logs:
- macOS:
~/Library/Logs/Claude/ - Windows:
%APPDATA%/Claude/Logs/ - Linux:
~/.config/Claude/Logs/
- macOS:
"Command not found" errors?
- Ensure Node.js 22+ is installed:
node --version - Try with npx:
npx @bowlly/mcp-server --setup - Global install fallback:
npm install -g @bowlly/mcp-server
Configuration not persisting?
- Check file permissions - Ensure you have write access to the config directory
- Use absolute paths - Relative paths may not resolve correctly
- Validate JSON format - Missing commas or brackets are common issues
License
MIT
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.