DigiSnap-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_TRANSPORT | No | Set to http to enable the remote Streamable HTTP transport for Grok. Defaults to stdio for local development. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_storesA | List currently registered shopping-store adapters. |
| search_digikalaC | Search Digikala and return normalized products. |
| get_digikala_productC | Get one normalized Digikala product. |
| search_snappshopC | Search SnappShop and return normalized products. |
| get_snappshop_productC | Get one normalized SnappShop product with variants and offers. |
| compare_productsC | Compare products across stores, including identity, variants, specs and offers. |
| compare_offersC | Compare normalized offers across the supplied store products. |
| compare_pricesD | Backward-compatible price comparison using the canonical comparison engine. |
| find_best_priceC | Find the lowest comparable observed offer under explicit filters. |
| find_best_valueC | Select an offer using an explicit, ordered policy rather than a hidden score. |
| analyze_offersC | Expose observed discount, availability, warranty and seller signals without ranking. |
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 11 tools
The two store-specific search/get tools are clearly distinct, but the comparison cluster (compare_products, compare_offers, compare_prices) and ranking/value tools (find_best_price, find_best_value) have subtle boundaries. Descriptions help distinguish them, but an agent could still hesitate between compare_prices and compare_offers or between the two find_best tools.
All tool names use snake_case with a predictable verb_noun structure, such as search_digikala, get_digikala_product, compare_offers, and find_best_price. Minor variations like search_digikala omitting 'product' are natural and do not break the pattern.
With 11 tools, the set is well-scoped for a multi-store product search and comparison server. Each tool appears to earn its place, covering store listing, per-store search/get, cross-store comparison, and offer analysis without excessive bloat.
The surface covers the read-only shopping comparison lifecycle well: list stores, search and get products per store, compare products/offers/prices, and analyze or select best offers. Minor gaps exist, such as no generic cross-store search tool or store-adapter management, but core workflows are covered.