VOC Amazon Reviews — Agent-Native Review Intelligence
Fetch and analyze verified Amazon reviews from 10 marketplaces (US, CA, MX, GB, DE, FR, IT, ES, JP, AU) via real Shulex OpenAPI — not scrapers. Built for AI agents running Amazon-seller workflows.
What it does
| Tool | What it does |
|---|---|
fetch_reviews | Pull verified Amazon reviews for any ASIN, up to 1000 per call |
analyze_reviews | Turn raw reviews into structured VOC reports (themes, sentiment, complaints) |
voc_full | One-shot fetch + analyze for ad-hoc seller questions |
extract_listing_improvements | Generate copy-ready title, 5 bullets, description — grounded in real customer language. Uses Claude Opus 4.7 + proprietary rubric distilled from Shulex's 2B-review corpus |
analyze_csv | Run VOC analysis on any CSV/Excel (Walmart, Shopify, support tickets) |
render_dashboard | Generate standalone HTML dashboards |
Why it's different
- Real OpenAPI access, not DOM scraping — won't break when Amazon changes HTML
- Verified-purchase, Vine, helpful-vote, variant signals included in every review
- Proprietary listing rubric trained on 2B+ historical Amazon reviews (data indexed before Amazon's access restrictions; cannot be replicated by buying API access today)
- Agent-first design — tool schemas, error codes, and metadata optimized for LLM router selection
Installation (one line)
Add this to your MCP client config (Claude Code, Cursor, Cline):
{
"mcpServers": {
"voc-amazon-reviews": {
"command": "uvx",
"args": [
"voc-amazon-reviews-mcp"
],
"env": {
"VOC_API_KEY": "your-shulex-key",
"ANTHROPIC_API_KEY": "your-anthropic-key"
}
}
}
}
Requires uv (install). First run pulls the repo and resolves deps in ~10s; subsequent runs are instant.
Get a free Shulex API key (100 calls/month, no credit card): apps.voc.ai/openapi
Example workflows
Listing rewrite: "Pull reviews of my ASIN and the top 3 competitors. Rewrite my listing to attack their weak points." → agent calls fetch_reviews × 4 → analyze_reviews × 4 → extract_listing_improvements → complete listing draft.
Daily monitoring: Schedule voc_full × 10 ASINs daily via cron; alerts on new negative theme clusters.
Competitor gap analysis: "What do customers complain about in this category that no top seller addresses?" → fetch_reviews × 5 → analyze_reviews → list of unaddressed pain points.
License
MIT
Server Config
{
"mcpServers": {
"voc-amazon-reviews": {
"command": "uvx",
"args": [
"voc-amazon-reviews-mcp"
],
"env": {
"VOC_API_KEY": "your-shulex-key",
"ANTHROPIC_API_KEY": "your-anthropic-key"
}
}
}
}