PluginBench
MCP Server
Maintained

VOC Amazon Reviews MCP Server

io.github.mguozhen/voc-amazon-reviews-mcp

Agent-native voice-of-customer intelligence for Amazon reviews across 10 marketplaces.

RepositoryRegistry
How to choose

What this kind of tool is for

  • Let your agent search the web or a document set and cite what it found.
  • Pull structured facts out of pages instead of copy-pasting by hand.
  • Track changes on a topic over days without re-reading everything.

How to compare servers like this

Source coverage:
Check which engines, sites, or document types the tool can actually reach.
Citation behavior:
Prefer tools that return links you can open, not just summarized claims.
Terms of service:
Some sources forbid automated access; make sure the tool stays inside them.
Maintenance signal:
Scrapers break silently when pages change; recent commits are the best proxy.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the VOC Amazon Reviews MCP server?

The VOC Amazon Reviews MCP server is an agent-callable tool for analyzing Amazon product reviews and generating voice-of-customer insights. It fetches reviews from 10 Amazon marketplaces via the Shulex VOC OpenAPI, analyzes sentiment and pain points, and generates copy-ready listing improvements and interactive HTML dashboards.

This server brings professional VOC (voice-of-customer) analysis to Claude, Cursor, and other MCP clients. Drop in an ASIN or upload a CSV of reviews from any platform, and get structured sentiment analysis, customer pain points, AI-generated listing copy improvements, and a standalone HTML dashboard—all callable by agents in real time.

How to install VOC Amazon Reviews

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • VOC_API_KEY
    required
    secret

    Shulex VOC OpenAPI key. Get a free one (100 calls/month, no credit card) at https://apps.voc.ai/openapi

  • ANTHROPIC_API_KEY
    secret

    Anthropic API key. Only needed if you use extract_listing_improvements (which uses Claude Opus 4.7 for structured listing rewrites).

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "voc-amazon-reviews-mcp": {
      "command": "uvx",
      "args": [
        "voc-amazon-reviews-mcp"
      ],
      "env": {
        "VOC_API_KEY": "<YOUR_VOC_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • fetch_reviews — Fetch raw Amazon reviews for an ASIN from 10 marketplaces via Shulex VOC OpenAPI.
  • analyze_reviews — Analyze a set of reviews to extract sentiment, pain points, and VOC insights.
  • voc_full — Complete VOC report in one call: fetch reviews and analyze them together.
  • extract_listing_improvements — Generate copy-ready title, bullet points, and description grounded in customer language and pain points.
  • analyze_csv — Analyze reviews from a CSV or Excel file with fuzzy column detection (supports any platform: Helium 10, eBay, Shopify, custom).
  • render_dashboard — Generate a standalone black-gold HTML dashboard from a VOC report with no external dependencies.

Use cases

  • Analyze Amazon product reviews across 10 markets to identify customer pain points and sentiment trends.
  • Generate AI-powered listing improvements (title, bullets, description) grounded in verified customer feedback.
  • Upload reviews from non-Amazon platforms (eBay, Shopify, Helium 10 exports) and get the same VOC analysis.
  • Create interactive HTML dashboards to visualize review sentiment, tags, and improvement opportunities.
  • Batch-process multiple ASINs or CSV files to compare VOC insights across products.

VOC Amazon Reviews MCP server FAQ

What is the VOC Amazon Reviews MCP server?

It's an MCP-callable tool that fetches Amazon reviews from 10 marketplaces and generates voice-of-customer reports with sentiment analysis, pain points, listing improvements, and HTML dashboards.

Is it free?

The server itself is open-source (MIT). It requires a free Shulex VOC API key (100 calls/month, no credit card). The `extract_listing_improvements` tool optionally uses Claude API (Anthropic key required) for ~$0.05–0.20 per listing.

How do I install it in Cursor or Claude?

Add the MCP server config to your client (Claude Desktop, Cursor, Cline, etc.) with `uvx voc-amazon-reviews-mcp` and set `VOC_API_KEY` environment variable. Get a free Shulex key at apps.voc.ai/openapi.

What if I don't have an ASIN?

Use the `analyze_csv` tool to upload reviews from any platform (CSV or Excel). It auto-detects review columns in any language and fuzzy-matches headers like 'review', 'content', '评价', etc.

Can I use it without an Anthropic API key?

Yes. Five of the six tools work without it. Only `extract_listing_improvements` (AI-generated listing copy) requires an Anthropic key.

What data does it capture?

Reviews include verified-purchase signals, Vine status, helpful votes, variant info, dates, and full text. The VOC report extracts sentiment, 22-dimension tags, and pain points.

README (reference)

Source of truth, from the repository.

<p align="center"> <img src="docs/logo-400.png" width="120" alt="Review Analyzer"> </p> <h1 align="center">Review Analyzer</h1> <p align="center"> <strong>Agent-native voice-of-customer for e-commerce.</strong><br> <em>Drop in an ASIN or a CSV — get sentiment, pain points, copy-ready listing improvements,<br> and a black-gold HTML dashboard. 6 MCP tools. Backed by the most stable Amazon review data layer.</em> </p> <p align="center"> <a href="#quick-start"><img src="https://img.shields.io/badge/setup-30s-brightgreen?style=flat-square" alt="30s Setup"></a> <a href="#tools"><img src="https://img.shields.io/badge/MCP%20tools-6-FF6A00?style=flat-square" alt="6 MCP tools"></a> <a href="#data-layer"><img src="https://img.shields.io/badge/markets-10-FF9900?style=flat-square&logo=amazon&logoColor=white" alt="10 Markets"></a> <a href="https://github.com/cline/mcp-marketplace/issues/1602"><img src="https://img.shields.io/badge/Cline-submitted-1976d2?style=flat-square" alt="Cline"></a> <a href="https://github.com/punkpeye/awesome-mcp-servers/pull/6528"><img src="https://img.shields.io/badge/awesome--mcp--servers-PR%20%236528-blueviolet?style=flat-square" alt="awesome-mcp-servers"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green?style=flat-square" alt="MIT"></a> </p> <p align="center"> <a href="docs/screenshots/dashboard.png"> <img src="docs/screenshots/dashboard.png" alt="Dashboard preview" width="100%"> </a> </p> <p align="center"><sub>↑ Sample dashboard: B08N5WRWNW · 100 reviews · sentiment + pain points + listing improvements, generated by <code>render_dashboard</code>.</sub></p>

TL;DR

Two inputs, six tools, three outputs.

   ┌─────────────┐                                            ┌──────────────┐
   │   ASIN      │──┐                                       ┌─│ Markdown     │
   └─────────────┘  │      ┌─────────────────────────┐      │ │ report       │
                    ├──────▶ 6 agent-callable tools  ├──────┤ ├──────────────┤
   ┌─────────────┐  │      └─────────────────────────┘      │ │ Structured   │
   │  CSV / XLSX │──┘   fetch_reviews   analyze_csv         │ │ JSON         │
   └─────────────┘      analyze_reviews voc_full            │ ├──────────────┤
                        extract_listing_improvements        └─│ Black-gold   │
                        render_dashboard                      │ HTML deck    │
                                                              └──────────────┘
  • Inputs — Amazon ASIN (auto-fetched via Shulex VOC OpenAPI, 10 markets) or any review CSV / Excel (Helium 10 / eBay / Shopify / custom — fuzzy column detection)
  • Outputs — Markdown report · structured JSON · standalone HTML dashboard
  • Surface — MCP server (works in Claude Code / Cursor / Cline / Continue) and Skill (works in Claude Code)

Quick start

Option A — As an MCP server (recommended)

Requires uv.

Add this to your MCP client config (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code Copilot, Cline, Continue.dev):

{
  "mcpServers": {
    "voc-amazon-reviews": {
      "command": "uvx",
      "args": ["voc-amazon-reviews-mcp"],
      "env": {
        "VOC_API_KEY": "your-shulex-key"
      }
    }
  }
}

Get a free Shulex API key (100 calls/month, no credit card): apps.voc.ai/openapi.

Optional: Add "ANTHROPIC_API_KEY": "sk-ant-..." to enable extract_listing_improvements (the only tool that calls Claude directly — others work without it). Must be an actual Anthropic key; other providers won't work.

First run resolves dependencies in ~5s; subsequent runs are instant.

Try it

Ask any MCP-compatible agent:

Run a VOC report on B08N5WRWNW, render the dashboard, and write it to ~/Desktop/voc.html.

The agent will call voc_full → render_dashboard and hand you the file.

Option B — One-shot CLI

bash voc.sh B08N5WRWNW --limit 100 --market US

Option C — Bring your own reviews (CSV)

# Drop in any reviews CSV (Helium 10 export, eBay scrape, Shopify, custom)
python -c "from mcp_server.tools import analyze_csv, render_dashboard; \
  r = analyze_csv('reviews.csv', product_name='My Product'); \
  render_dashboard(r, output_path='dashboard.html')"

Option D — Hosted on Smithery (no install)

Connect to the server remotely — no uvx, no Python, no local install. Bring your own Shulex API key (Smithery prompts for it on first connection).

This repo ships a Dockerfile and smithery.yaml for one-click deploy. To run your own hosted instance:

  1. Fork or clone this repo to your GitHub.
  2. Sign in at smithery.ai with GitHub.
  3. Deploy a server → pick the repo. Smithery builds the container and exposes an HTTPS MCP endpoint.
  4. Share the URL with users; they paste it into Claude / Cursor / Cline.

The same image runs anywhere that takes a Dockerfile — Fly.io, Railway, Cloudflare Workers (with adapter), Render, Cloud Run.

To run the HTTP transport locally (e.g. for testing):

MCP_TRANSPORT=streamable-http PORT=8080 python -m mcp_server.server

Option E — Deploy to Vercel (serverless)

This repo also ships vercel.json + app.py for one-click Vercel deploys. Sign in at vercel.com with GitHub, import the repo, and Vercel auto-detects the Python function.

Set these in Project Settings → Environment Variables before the first deploy:

VariableRequiredNotes
VOC_API_KEYyesShulex VOC OpenAPI key
ANTHROPIC_API_KEYoptionalOnly for extract_listing_improvements

Timeout caveat: Vercel functions cap at 10s (Hobby default), 60s (Hobby with maxDuration: 60 — already set in vercel.json), or 300s (Pro). Long-running tools like voc_full (30-90s) and extract_listing_improvements (20-60s) may exceed these limits. For unbounded execution, prefer Option D (Docker/Render/Fly) or local install.

The MCP endpoint after deploy: https://your-project.vercel.app/mcp


Tools

#ToolInputUse when
1fetch_reviewsASINYou want raw reviews; you'll analyze them yourself
2analyze_reviewsreviews JSONYou already have reviews and want the VOC report
3voc_fullASINDefault "give me a VOC report" — fetch + analyze in one call
4extract_listing_improvementsASIN★ Differentiator — copy-ready title / 5 bullets / description grounded in customer language
5analyze_csvCSV / Excel path or URLThe product is NOT on Amazon, or you have your own scrape
6render_dashboardVOC reportGenerate a standalone black-gold HTML dashboard, no external deps

All 6 tools speak MCP. All return JSON-serializable dicts. Full schemas in mcp_server/README.md.


Data layer — why this is the moat

Most "AI review tools" are a thin LLM wrapper over a brittle scraper. We invert that. The data layer is the moat:

Typical seller-tool data layerreview-analyzer
SourceWeb scraper / undocumented scrape APIPaid Shulex VOC OpenAPI
ReliabilityBreaks when Amazon updates HTMLAPI-grade, no DOM dependencies
MarketsUS-only or 2-3 markets10: US, CA, MX, GB, DE, FR, IT, ES, JP, AU
Volume10–50 reviews (free-tier cap)Up to 1,000 reviews per ASIN
FreshnessDaily snapshots, sometimes cached for daysLive pull
SchemaStrings onlyFull: verified-purchase, helpful votes, vine, variant, dates
Non-English marketsOften broken / omittedNative captures + AI translation
AccessLocked behind a UIcurl + JSON, fully scriptable, MCP-ready

For non-Amazon platforms, analyze_csv accepts any review file — fuzzy column matching detects 内容 / 评价 / body / review / content so you don't have to reformat. Bring data from anywhere, get the same VOC report.


vs. the alternatives

review-analyzerHelium 10 / Data Divereview-analyzer-skill (Buluu)Generic review scrapers
InputASIN or CSVASIN (manual UI)CSV onlyURL
Markets101-3depends on user's data1
OutputJSON + Markdown + HTML dashboardUI dashboard (locked)CSV + MD + HTML dashboardRaw CSV
MCP-callable✅❌❌ Claude Code only❌
Listing copy gen✅ extract_listing_improvements (cite-by-pain-point)Keyword research only❌❌
CostShulex API + Anthropic API ($0.05-0.20/listing)$99-249/month subscriptionFree (uses your Claude quota)Free, brittle
Open source✅ MIT❌✅ MITvaries

Credit & inspiration: The 22-dimension tag system, fuzzy CSV column detection, and black-gold dashboard aesthetic were inspired by buluslan/review-analyzer-skill (MIT). We adapted them onto an MCP-native architecture with the Shulex VOC OpenAPI data layer.


Architecture

mcp_server/
├── server.py                  # 6 @mcp.tool decorators
├── tools.py                   # implementations (subprocess wrappers + Anthropic SDK)
├── csv_loader.py              # fuzzy column detection for CSV/Excel input
├── dashboard.py               # HTML rendering
├── dashboard_template.html    # black-gold template (placeholders)
├── tag_system.yaml            # 22-dim tag schema (customizable per category)
├── schemas.py                 # pydantic structured-output models
└── tests/                     # 36 unit tests (subprocess + Anthropic mocked)

fetch.sh / analyze.sh / voc.sh   # shell pipeline behind tools 1-3
  • fetch + analyze loop: shell scripts (proven, reproducible, easy to debug)
  • listing rewrites: Anthropic SDK direct (claude-opus-4-7 + adaptive thinking + prompt caching on the system rubric)
  • dashboard: pure stdlib HTML rendering, no node / no react

Distribution / where to find us

ChannelStatus
punkpeye/awesome-mcp-servers PR #6528✅ Open
cline/mcp-marketplace issue #1602✅ Open
Glama🟢 Auto-indexed via GitHub topics
mcp.directory🟢 Auto-pull
mcp.so / PulseMCP🟡 Pending (manual form submit)
Smithery🟡 Container deploy ready (smithery.yaml + Dockerfile in repo)
Official MCP Registry🟡 Pending PyPI publish (W2)

Roadmap

  • Drop in CSV / Excel (any platform, fuzzy column detect)
  • 22-dimension tag system (YAML-configurable)
  • Black-gold HTML dashboard tool
  • 6 MCP tools shipped
  • npx skills add mguozhen/review-analyzer one-line install
  • CLI subprocess engine option (use your Claude subscription, $0 API)
  • PyPI publish + official MCP Registry submission
  • Smithery deploy config (smithery.yaml + Dockerfile)
  • Vercel deploy config (vercel.json + app.py)
  • Smithery / mcp.so / PulseMCP form submissions

License

MIT. See LICENSE.

Acknowledgments: Tag schema, CSV column detection, and dashboard visual design inspired by buluslan/review-analyzer-skill. Data layer powered by Shulex VOC OpenAPI.

<!-- mcp-name: io.github.mguozhen/voc-amazon-reviews-mcp -->

Related MCP servers

Google Search Console MCP: search analytics, URL inspection, site management.

1
JavaScript
MIT
View repository →
COContextPull logo

Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.

0
HTML
MIT
View repository →
NONobodyNamed logo

US baby name popularity data from SSA records (1880-2025): search, trends, geography, culture.

0
HTML
MIT
View repository →

Citation-network analysis on Scopus or OpenAlex: coupling, co-citation, lineages, bibliometrics.

0
Python
MIT
View repository →

AI-powered H-E-B grocery shopping—search products, manage carts, and clip coupons through natural conversation.

50
Python
MIT
View repository →

Embedded/IoT mentor: picks the board and toolchain, estimates cost and battery life.

0
Python
MIT
View repository →