Loading ToolBench
MCP server for Shopify App Store intelligence — search 17k+ apps, 829k+ reviews, rankings, and review sentiment via PartnerLens; plus your own Partner Dashboard installs/MRR/churn on paid plans. Free API key at https://www.partnerlens.app
PartnerLens MCP demonstrates solid tool design with consistent naming conventions (all verb_noun), comprehensive parameter schemas using Zod, and clear descriptions. All 9 tools have explicit descriptions (avg ~180 chars, within baseline 194). Input schemas are fully defined with type constraints, ranges, and regex patterns. However, output schemas are not documented, LLMs cannot see what fields to expect from responses. Error handling is minimal (no recovery guidance, no categorization). Tool descriptions lack dependency hints and prerequisites. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite all tools being read-only. Composition is strong: tools chain well (search_apps → get_app → get_app_reviews), and parameter naming is consistent (slug pattern reused). Security is sound: no secrets in parameters, all tools are read-only. Missing: output schema documentation, error recovery guidance, tool annotations.
Compare 2-5 Shopify apps side by side: metadata plus each app's aggregate review summary. Ideal for competitor analysis.
Get full details for one Shopify app by slug: description, developer, rating, review count, categories, Built-for-Shopify status, launch date, and its latest rank in its primary category.
Read individual reviews for a Shopify app, newest first. Optionally filter by star rating (e.g. rating=1 surfaces complaints and churn reasons; rating=5 surfaces what users love). Paged.
List YOUR OWN apps synced from your Shopify Partner organization (name, handle, partner app id). Requires a PartnerLens Unlimited plan and the Shopify Partner integration connected in Settings → Integrations. Returns an empty list until the integration has synced. Use the returned id with get_my_metrics.
YOUR OWN private daily Partner Dashboard metrics: installs, uninstalls, active shops, gross/net revenue, MRR with movement breakdown (new/expansion/contraction/churned), and churn rate. Defaults to the last 30 days (max 366). Requires a PartnerLens Unlimited plan with the Shopify Partner integration connected. Combine with public tools to compare your performance against competitors.
Output schemas not documented. LLMs cannot see what fields to expect from tool responses (e.g., does get_app return 'rating' or 'avg_rating'? Does get_app_reviews return paginated results with 'total_count'?). This forces LLMs to guess field names and risks broken downstream tool chains.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All 9 tools are read-only and idempotent, but this is not declared in the schema. Clients cannot optimize caching or retry logic without explicit hints.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 66 | 2026-07-28+ | v2 |
Aggregate review intelligence for a Shopify app: rating distribution, sentiment breakdown (positive/negative/neutral), review velocity per month for the last 12 months, and the top AI-extracted pain points. Much cheaper than reading raw reviews — start here for app health.
Current top-ranked apps in a Shopify App Store category, from the latest scrape. Returns position, app metadata, rating, and review count.
List all Shopify App Store categories with app counts, largest first. Use the returned slugs with get_top_apps.
Search the Shopify App Store dataset (17k+ apps) by app name, developer name, or slug. Returns matching apps with rating, review count, and categories. Use this first to resolve an app name to its slug.
Error handling lacks recovery guidance. No tool documents what errors are possible, whether they are retryable, or what the LLM should do next. E.g., if get_app fails with 'app not found', should the LLM retry search_apps? This is not stated.
Descriptions lack dependency hints and prerequisites. E.g., get_my_apps and get_my_metrics require 'PartnerLens Unlimited plan' and 'Shopify Partner integration connected', but do not explain what error to expect if these are missing or how to resolve it. Descriptions should guide LLM planning.
Pagination not fully specified. get_app_reviews accepts page/per_page but does not document whether the response includes total_count or next_cursor. Without this, LLMs cannot determine if more results exist or how to fetch them efficiently.