Skip to main content
Glama
StoreSignal MCP Server

StoreSignal MCP Server

by anthesiallc

StoreSignal MCP Server

mcp-name: io.github.anthesiallc/storesignal

A Model Context Protocol server that exposes the StoreSignal API as tools, so any MCP client (Claude Desktop, Cursor, ChatGPT connectors, or an agent framework) can analyze Shopify stores and run market intelligence queries conversationally.

It's a thin wrapper: each tool maps to one StoreSignal REST endpoint. All the data work happens in the API.

Tools

Tool

What it does

analyze_store

Full structured profile for a Shopify store URL (apps, CDN, security headers, schema.org, classification, revenue estimate)

compare_stores

Side-by-side comparison of 2-5 stores (shared apps, exclusive apps, tier)

find_stores_using_app

Paginated list of every analyzed store running a specific app

list_apps

All 278 apps in the catalog, optionally filtered by category

app_adoption

Top apps by adoption % across the corpus, optionally filtered by category

app_vs_app

Head-to-head: install counts, overlap, co-install rate, bidirectional cross-adoption

industry_overview

Per-vertical stats: store count, median price, top countries, top apps, tier mix

store_census

Whole-corpus stats (19,647 stores, 20 industries, app/tier/type breakdowns)

get_usage

Current billing period usage and plan limit

Related MCP server: Clind MCP Server

Get an API key

Free tier is 250 calls/month, no credit card:

curl -X POST https://storesignal.anthesia.io/api/v1/signup \
  -H 'Content-Type: application/json' \
  -d '{"email":"you@example.com"}'

The key comes back in the api_key field of the response.

Install and run

The easiest way is with uv (no manual venv needed):

# stdio transport (default — for Claude Desktop, Cursor, most local clients)
STORESIGNAL_API_KEY=ss_your_key uvx storesignal-mcp

# streamable-HTTP transport (for remote / web clients)
STORESIGNAL_API_KEY=ss_your_key uvx storesignal-mcp --http

Or install with pip into its own environment:

pip install storesignal-mcp
STORESIGNAL_API_KEY=ss_your_key storesignal-mcp

Note: install into a dedicated environment. The mcp SDK requires a newer starlette than the StoreSignal API app pins, so the two will conflict if installed together.

Environment variables:

  • STORESIGNAL_API_KEY (required) — your StoreSignal API key.

  • STORESIGNAL_BASE_URL (optional) — defaults to https://storesignal.anthesia.io.

  • STORESIGNAL_TIMEOUT (optional) — request timeout in seconds, default 60.

Client configuration

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "storesignal": {
      "command": "uvx",
      "args": ["storesignal-mcp"],
      "env": { "STORESIGNAL_API_KEY": "ss_your_key" }
    }
  }
}

Cursor

Add the same block to ~/.cursor/mcp.json (or the project .cursor/mcp.json).

Smithery (hosted, no install)

The server is hosted on Smithery, so MCP clients that support Smithery can connect without installing anything. You provide your StoreSignal API key in the Smithery config and it routes to the server.

LangChain / LangGraph

Any LangChain or LangGraph agent can use these tools through langchain-mcp-adapters:

# pip install langchain-mcp-adapters langgraph "langchain[anthropic]"
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient(
    {
        "storesignal": {
            "transport": "stdio",
            "command": "uvx",
            "args": ["storesignal-mcp"],
            "env": {"STORESIGNAL_API_KEY": "ss_your_key"},
        }
    }
)
tools = await client.get_tools()
# hand `tools` to a LangGraph/LangChain agent, e.g.
# from langgraph.prebuilt import create_react_agent
# agent = create_react_agent("anthropic:claude-opus-4-8", tools)

LlamaIndex works the same way via its MCP tool spec.

Example agent conversations

"What apps does Allbirds use?" → analyze_store("https://www.allbirds.com")

"Compare the tech stacks of Brooklinen and Bombas." → compare_stores(["https://brooklinen.com", "https://bombas.com"])

"Which Shopify stores are running Judge.me?" → find_stores_using_app("judge-me")

"What are the top email-marketing apps on Shopify?" → app_adoption(category="Email Marketing")

"Compare Klaviyo to Omnisend." → app_vs_app("klaviyo", "omnisend")

"Tell me about the Beauty vertical." → industry_overview("Beauty")

Develop from source

git clone https://github.com/anthesiallc/storesignal-mcp && cd storesignal-mcp
python -m venv .venv
.venv/Scripts/python -m pip install -e ".[http]"   # Windows; [http] adds uvicorn for --http
# .venv/bin/pip install -e ".[http]"                # macOS/Linux
STORESIGNAL_API_KEY=ss_your_key .venv/Scripts/python -m storesignal_mcp.server

Notes

  • Data is extracted only from publicly accessible Shopify storefront endpoints.

  • Not affiliated with Shopify Inc.

  • The LLM-classification endpoints (industry / store type / growth stage) are intentionally not exposed as MCP tools. The agent calling MCP is already an LLM and can reason about the raw corpus data itself — exposing them would waste tokens on a round trip to OpenAI.

Available Tools

9 tools
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".

Inputs: url (required). Returns: object

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).

Inputs: category, limit. Returns: object

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").

Inputs: app_a (required), app_b (required). Returns: object

compare_storesA

Side-by-side comparison of 2-5 Shopify stores.

Returns each store's profile plus a comparison table: shared apps, apps unique to each, payment-provider overlap, tier comparison. Good for "compare https://A and https://B" or competitive recon questions.

Args: urls: 2-5 Shopify store URLs to compare.

Inputs: urls (required). Returns: object

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.

Inputs: app_slug (required), limit, offset. Returns: object

get_usageB

Show this API key's current billing period usage and plan limits.

Inputs: no named parameters. Returns: object

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.

Inputs: industry (required). Returns: object

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).

Inputs: category, limit. Returns: object

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.

Inputs: no named parameters. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 9 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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.

    Related MCP Connectors

    Related MCP Servers