stashdog-mcp-server
StashDog MCP Server - Natural language interface for inventory management
Documentation
StashDog MCP Server
A Model Context Protocol (MCP) server that provides natural language tools for managing your StashDog inventory. This server enables AI assistants to interact with your StashDog inventory through intuitive natural language commands.
๐ Features
- Natural Language Interface: Use plain English to manage your inventory
- Comprehensive Item Management: Add, update, search, delete, and organize items
- Collection Management: Create and manage collections with ease
- Smart Search: Intelligent search across your inventory with complex queries
- Tag Management: Create, rename, and organize tags
- URL Import: Import items directly from URLs
- Authentication: Secure authentication with your StashDog account
- Rich Formatting: Beautiful, formatted responses with emojis and structured data
๐ ๏ธ Installation
1. Clone or download this MCP server to your local machine:
git clone
cd stashdog-mcp-server2. Install dependencies:
npm install3. Build the server:
npm run build4. Configure environment variables:
cp .env.example .env
# Edit .env with your StashDog API configurationโ๏ธ Configuration
Environment Variables
Create a `.env` file in the root directory:
# StashDog Supabase Configuration
STASHDOG_SUPABASE_URL=http://localhost:54321
STASHDOG_SUPABASE_ANON_KEY=your_anon_key_here
STASHDOG_AUTH_TOKEN=your_auth_token_here
# Optional: Pre-configured credentials
STASHDOG_EMAIL=your_email@example.com
STASHDOG_PASSWORD=your_passwordThis server only uses user access tokens for requests. Do not provide a service role key.
MCP Client Configuration
Add this server to your `.cursor/mcp.json` or similar MCP client configuration:
{
"mcpServers": {
"stashdog": {
"command": "node",
"args": ["/path/to/stashdog-mcp-server/dist/index.js"],
"env": {
"STASHDOG_SUPABASE_URL": "http://localhost:54321",
"STASHDOG_SUPABASE_ANON_KEY": "your_anon_key_here",
"STASHDOG_AUTH_TOKEN": "your_token_here"
}
}
}
}๐ง Available Tools
1. `authenticate`
Authenticate with your StashDog account.
Example:
authenticate with email: user@example.com and password: mypassword2. `manage_inventory_items`
Add, update, search, delete, or manage inventory items using natural language.
Examples:
- `"Add a new MacBook Pro with tags electronics, work, expensive"`
- `"Search for items tagged with kitchen"`
- `"Update item abc123 to add note about warranty expiring soon"`
- `"Delete item xyz789"`
- `"Find all storage containers"`
- `"Add item called 'Wireless Mouse' with notes 'Logitech MX Master 3' and tags office, electronics"`
3. `manage_collections`
Create, update, delete collections or manage items within collections.
Examples:
- `"Create a new collection called 'Kitchen Appliances'"`
- `"Add items abc123, def456 to collection xyz789"`
- `"Delete collection old-stuff"`
- `"Update collection xyz789 to change name to 'Home Office'"`
4. `import_from_url`
Import items from URLs (product pages, images, etc.).
Example:
import_from_url: https://example.com/product/laptop5. `manage_tags`
Create, search, rename, or delete tags.
Examples:
- `"Create tag electronics"`
- `"Search for tags containing kitchen"`
- `"Rename tag old-name to new-name"`
- `"Delete tag unused-tag"`
6. `get_inventory_stats`
Get statistics about your inventory.
Example:
get_inventory_stats7. `smart_search`
Perform intelligent searches with natural language queries.
Examples:
- `"Show me all electronics in the office"`
- `"Find kitchen items that are favorited"`
- `"List storage containers with more than 5 items"`
8. `manage_users`
Fetch user details.
Example:
manage_users with userId: abc1239. `manage_notifications`
Fetch user notifications.
Examples:
- `"Fetch all unread notifications"`
- `"Get notifications with a limit of 10"`
10. `manage_groups`
Fetch user groups.
Example:
manage_groups11. `manage_subscriptions`
Manage subscriptions including fetching details and creating subscriptions.
Examples:
- `"Get subscription details for US in USD"`
- `"Create a subscription with tier PREMIUM"`
๐ Usage Examples
Adding Items
Add a new item called "Gaming Keyboard" with notes "Mechanical switches, RGB lighting" and tags gaming, electronics, desk-setupSearching Items
Find all items tagged with electronics that are in storage containersManaging Collections
Create a new collection called "Home Office Setup" with description "Everything needed for working from home"Complex Operations
Search for items with tags kitchen, appliances limit 10๐ฏ Natural Language Parsing
The server includes sophisticated natural language parsing that understands:
- Actions: add, create, update, modify, delete, remove, search, find, favorite, etc.
- Tags: Supports `#hashtag` format and comma-separated lists
- Item IDs: Automatically detects UUIDs in various formats
- Custom Fields: Parses `field_name: value` patterns
- Storage Indicators: Recognizes storage/container keywords
- Quotes: Handles quoted names and descriptions
- Limits and Offsets: Understands pagination keywords
๐ Authentication
The server supports multiple authentication methods:
1. Environment Token: Set `STASHDOG_AUTH_TOKEN` in your environment
2. Runtime Authentication: Use the `authenticate` tool to log in
3. Auto-login: Configure `STASHDOG_EMAIL` and `STASHDOG_PASSWORD` for automatic authentication
๐ Response Format
All responses follow a consistent format:
{
"success": true,
"message": "โ
Successfully added item 'Gaming Keyboard' with ID: abc123",
"data": {
"id": "abc123",
"name": "Gaming Keyboard",
"tags": ["gaming", "electronics", "desk-setup"]
}
}๐ Error Handling
The server provides detailed error messages for common scenarios:
- Missing required parameters
- Authentication failures
- Network connectivity issues
- Supabase REST errors
- Validation errors
๐ Project Structure
stashdog-mcp-server/
โโโ src/
โ โโโ index.ts # Main MCP server
โ โโโ client.ts # Supabase REST client wrapper
โ โโโ types.ts # TypeScript types
โ โโโ nlp-utils.ts # Natural language processing
โ โโโ graphql/
โ โโโ operations.ts # Legacy GraphQL queries (unused)
โโโ dist/ # Compiled JavaScript
โโโ package.json
โโโ tsconfig.json
โโโ .env.example
โโโ README.md๐ Development
Running in Development Mode
npm run devBuilding
npm run buildTesting
npm test๐ค Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request
๐ License
MIT License - see LICENSE file for details.
๐ Support
If you encounter any issues:
1. Check that your StashDog API is running and accessible
2. Verify your authentication credentials
3. Check the server logs for detailed error messages
4. Ensure all dependencies are properly installed
๐ Examples in Action
Complete Workflow Example
# Authenticate
authenticate with email: user@example.com and password: mypassword
# Add some items
Add a new MacBook Pro with tags electronics, work, laptop and notes "16-inch, M2 chip, 32GB RAM"
# Create a collection
Create a new collection called "Work Equipment" with description "All items for remote work"
# Search for items
Find all items tagged with electronics
# Get stats
get_inventory_stats
# Import from URL
import_from_url: https://example.com/product/wireless-mouse
# Smart search
Show me all work-related items that are favoritedThis MCP server makes managing your StashDog inventory as easy as having a conversation with an AI assistant!
Frequently asked questions
What is stashdog-mcp-server?
stashdog-mcp-server is StashDog MCP Server - Natural language interface for inventory management
How do I install stashdog-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is stashdog-mcp-server open source?
Yes โ it is hosted on GitHub at https://github.com/dogfoodlab-io/stashdog-mcp-server.
Related MCP tools
Model Context Protocol Servers
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
MCP server to provide Figma layout information to AI coding agents like Cursor
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams โ everything you need to ship apps your users will love.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP