ShopGraph
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOOGLE_API_KEY | Yes | Gemini API key for LLM fallback | |
| STRIPE_TEST_SECRET_KEY | Yes | Stripe test mode secret key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| enrich_productA | Extract comprehensive product data from a URL including name, price, brand, images, availability, and more. Uses schema.org structured data when available, with LLM fallback. Costs $0.02 per call (cached results are free). |
| enrich_basicA | Extract basic product attributes from a URL (name, price, brand, availability). Faster and cheaper than enrich_product. Costs $0.01 per call (cached results are free). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: enrich_basic extracts minimal attributes quickly and cheaply, while enrich_product provides comprehensive data with advanced methods at higher cost. Their descriptions explicitly differentiate scope, method, and pricing, leaving no ambiguity for an agent to misselect.
Both tools follow a consistent verb_noun pattern with 'enrich_' prefix, maintaining perfect naming alignment. This predictability helps agents understand they belong to the same functional family for product data extraction.
Two tools are reasonable for a product data extraction server, offering tiered options. However, it feels slightly thin; additional tools like batch processing or schema validation could enhance completeness without overcomplication.
The server covers basic and comprehensive extraction well, but lacks tools for related operations like URL validation, batch processing, or data export. This creates minor gaps where agents might need workarounds for full workflows.