Brickognize MCP Server
This server identifies LEGO items from images using the Brickognize API and provides detailed information via the Rebrickable API.
Recognition
Health check (
brickognize_health): Verify the Brickognize API is onlineIdentify any item (
brickognize_identify): Recognize an unknown LEGO item (part, set, minifigure, or sticker) from a photoIdentify a part (
brickognize_identify_part): Precisely identify a specific brick or elementIdentify a set (
brickognize_identify_set): Recognize a LEGO set from its box, model, or instructionsIdentify a minifigure (
brickognize_identify_fig): Identify a specific minifigureBatch identify (
brickognize_batch_identify): Process up to 20 images in parallel in a single call
Lookup (requires Rebrickable API key)
Part details (
brickognize_part_details): Available colors and which sets contain a partBatch part details (
brickognize_batch_part_details): Retrieve details for multiple parts at onceSet details (
brickognize_set_details): Year, theme, and full parts inventoryMinifigure details (
brickognize_minifig_details): Minifigure info and which sets it appears in
Additional Features
Accepts local JPEG, PNG, or WebP files via absolute paths
Configurable caching (none, in-memory, or SQLite) for Rebrickable API responses
Cache clearing via
brickognize_cache_clearOptional raw API response output for debugging
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Brickognize MCP ServerIdentify the LEGO set in /Users/me/Desktop/lego_box.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Brickscope
Identify LEGO parts, sets, and minifigures from images — as a CLI tool or an MCP server for AI assistants.
Powered by the Brickognize API and Rebrickable.
Huge thanks to Piotr Rybak for creating the Brickognize service and making LEGO recognition accessible to everyone!
CLI
npm install -g brickscope
brickscope identify photo.jpg --type part
brickscope part 3001 --color Black
brickscope set 75192
brickscope minifig fig-012805Or run without installing: npx brickscope identify photo.jpg
MCP Server
For AI assistants (Claude, Cursor, etc.), add to your MCP config:
{
"mcpServers": {
"brickscope": {
"command": "npx",
"args": ["-y", "brickscope", "mcp"],
"env": {
"REBRICKABLE_API_KEY": "your-key-here",
"BRICKOGNIZE_CACHE": "sqlite"
}
}
}
}Configuration
Config file (CLI)
brickscope config initCreates ~/.config/brickscope/config.json with your Rebrickable API key and cache settings.
Environment variables
Variable | Default | Description |
| — | Free API key from rebrickable.com/api. Required for lookup tools. |
|
| Cache mode: |
Environment variables take priority over the config file.
Features
Image recognition — identify parts, sets, minifigures, and stickers from photos
Batch processing — identify multiple images in parallel
Part lookup — colors, set appearances via Rebrickable
Set inventory — full parts list, year, theme, piece count
Minifigure lookup — details and set appearances
Caching — in-memory or SQLite cache for Rebrickable API responses
Config file — save API key and preferences once, use everywhere
Examples
See the examples folder for prompt templates.
Development
npm install
npm run build
npm run dev # Watch mode
npm test # Unit + integration tests
npm run lint # ESLint
npm run format # PrettierLicense
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/NazarLysyi/brickognize-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server