Skip to main content
Glama
README.md
# Pangolinfo Amazon Reviews MCP

An official, read-only MCP server focused on Amazon review research and voice-of-customer (VOC) signals. It gives AI agents a smaller, review-specialized tool surface while using the same authenticated Pangolinfo data engine as the broader [Amazon Data MCP](https://www.pangolinfo.com/amazon-data-mcp/).

## Tools

- `get_amazon_reviews` — paginated raw reviews
- `find_complaint_signals` — low-rating complaint evidence
- `summarize_review_ratings` — deterministic rating counts and averages
- `filter_review_media` — image/video evidence reviews
- `compare_review_pages` — side-by-side rating and complaint metrics for two ASINs

All tools are read-only. The bridge never stores API keys or result data. It forwards requests to the hosted MCP endpoint and performs deterministic local filtering only.

## Quick start

Get a Pangolinfo key from the [Amazon Review API page](https://www.pangolinfo.com/amazon-review-api/), then configure any MCP client:

```json
{
  "mcpServers": {
    "pangolinfo-amazon-reviews": {
      "command": "npx",
      "args": ["-y", "pangolinfo-amazon-reviews-mcp"],
      "env": { "PANGOLINFO_API_KEY": "<YOUR_API_KEY>" }
    }
  }
}
```

Or run `PANGOLINFO_API_KEY=... npx -y pangolinfo-amazon-reviews-mcp`. Docker and hosted HTTP setup are documented on the [Amazon Review API landing page](https://www.pangolinfo.com/amazon-review-api/) and [Pangolinfo docs](https://docs.pangolinfo.com/).

## Links

- Product: https://www.pangolinfo.com/amazon-review-api/
- Docs: https://docs.pangolinfo.com/
- Source: https://github.com/Pangolin-spg/amazon-reviews-mcp
- Amazon Data MCP: https://www.pangolinfo.com/amazon-data-mcp/

## License

MIT. Pangolinfo trademarks and logos remain subject to the brand guidelines in `BRANDING.md`.

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct action on Amazon review data: fetching raw pages, extracting complaints, summarizing ratings, filtering media, and comparing products. There is little risk of selecting the wrong tool for a task.

Naming Consistency5/5

All tool names follow a clear lowercase verb_noun pattern with descriptive, specific verbs: get, find, summarize, filter, compare. The naming is consistent and predictable across the entire set.

Tool Count5/5

Five tools is well-scoped for an Amazon reviews analysis server. Each tool covers a distinct aspect of the workflow without unnecessary redundancy or bloat.

Completeness4/5

The tool set covers core review retrieval, analysis, and comparison workflows well. Minor gaps exist around multi-page aggregation or deeper per-review detail, but agents can accomplish the main review-analysis tasks without dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues