StoreSignal MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STORESIGNAL_API_KEY | Yes | Your StoreSignal API key (required) | |
| STORESIGNAL_TIMEOUT | No | Request timeout in seconds (optional) | 60 |
| STORESIGNAL_BASE_URL | No | Base URL for the StoreSignal API (optional) | https://storesignal.anthesia.io |
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 |
|---|---|
| analyze_storeA | Analyze a single Shopify store URL and return a full structured profile. Returns the store's name, theme, product count, apps installed, payment + analytics + checkout providers, CDN brand, security headers, schema.org markup, AI-classified industry / store type / growth stage (paid tiers), revenue estimate, social media, and more. Use this as the default entry point when the user asks "what's this store using" or "tell me about https://...". If the URL is already in the 19K-store corpus the response is served from cache; otherwise the API runs a fresh crawl (5-15 seconds for new stores). Args: url: Shopify store URL, e.g. "https://www.allbirds.com". |
| compare_storesA | |
| find_stores_using_appA | List analyzed Shopify stores that have a specific app installed. Returns paginated stores (up to 100 per page) with the basic profile so the agent can do downstream filtering or rank by store tier / country / industry. Useful for prospecting: "find me stores running Klaviyo" or "who's using ReCharge Subscriptions in the apparel vertical". Args: app_slug: Catalog slug, e.g. "klaviyo", "judge-me", "loox", "yotpo", "recharge", "shogun", "pagefly". List all slugs with list_apps(). limit: Results per page (1-100). offset: Pagination offset. |
| list_appsA | List all apps in the StoreSignal catalog (currently 278 apps). Returns each app with its slug, display name, category, subcategory, estimated monthly cost tier, competing alternatives, and live install count across the corpus. Use this to discover what's trackable before calling find_stores_using_app or app_vs_app. Args: category: Optional category filter, e.g. "Email Marketing", "Reviews", "Payment", "Analytics", "Loyalty", "Privacy", "Fraud & Risk". limit: Max apps to return (1-200). |
| app_adoptionA | Percentage of analyzed Shopify stores using each app. Returns apps ranked by adoption percentage. For example, PayPal is on 99.6% of stores; Klaviyo 24.9%. Optionally filter by category to see (e.g.) only the email-marketing landscape. Args: category: Optional category to filter on (Email Marketing, Reviews, Payment, Analytics, Loyalty, etc). limit: Top-N apps to return (1-200). |
| app_vs_appA | Head-to-head comparison of two apps' installed bases. Returns: install count for each app, exclusive users (A only / B only), overlap (both installed), co-install rate (overlap as % of union), and bidirectional cross-adoption (% of A users that also run B, and vice versa). Good for competitive questions like "is Omnisend losing ground to Klaviyo?". The cross-install asymmetry is usually the most interesting number: if 44% of B users also run A but only 5% of A users run B, A is eating B's market from the inside. Args: app_a: Slug of the first app (e.g. "klaviyo"). app_b: Slug of the second app (e.g. "omnisend"). |
| industry_overviewA | Big-picture stats for one industry vertical. Returns: store count, median product count, median price (with p25/p75 quartiles), average domain age, country distribution, store-tier mix (small/medium/large), store-type mix (DTC/marketplace/dropshipper), and the top apps installed across the vertical. Use for questions like "what does the Beauty vertical look like on Shopify?" or "are Apparel stores mostly DTC or marketplaces?". Args: industry: One of: Apparel, Beauty, Home & Garden, Food & Beverage, Electronics, Pets, Fitness & Sports, Jewelry & Accessories, Toys & Games, Automotive, Health & Wellness, Outdoors & Adventure, Baby & Kids, Books & Stationery, Arts & Crafts, Music & Instruments, Office & Business, Travel & Luggage, Gifts & Novelty, Other. |
| store_censusA | High-level statistics for the entire analyzed-stores corpus. Returns: total stores indexed, count classified, distinct countries, distinct industries, total apps in the catalog, plus breakdowns (top 25 countries, all industries, tier mix, store-type mix, growth-stage mix). Useful when the agent or user wants to understand the dataset's scope before doing more targeted queries. |
| get_usageB | Show this API key's current billing period usage and plan limits. |
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 9 tools
Each tool has a clearly distinct purpose: analyzing a single store, comparing multiple stores, app adoption stats, head-to-head app comparison, finding stores by app, API usage, industry overview, app catalog listing, and corpus census. No two tools overlap in functionality.
All tool names follow a consistent snake_case verb_noun pattern (e.g., analyze_store, list_apps, compare_stores). The naming is clear and predictable, aiding agent selection.
With 9 tools, the set is well-scoped for the server's domain of Shopify store analytics. Each tool serves a necessary function without unnecessary bloat, covering store analysis, app intelligence, and dataset exploration.
The tools cover core workflows: single store analysis, comparison, app landscape, industry stats, and catalog browsing. Minor gaps exist (e.g., no direct search by country or tier), but the surface is sufficiently complete for the stated purpose.