Pangolinfo Review Mining MCP
OfficialProvides tools for mining Amazon product reviews by ASIN across supported marketplaces, including paginated review retrieval, complaint extraction from critical reviews, sentiment and rating summaries with monthly trends, ranked complaint topics, and combined per-ASIN review-mining reports.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pangolinfo Review Mining MCP mine complaints for ASIN B0FQFB8FMG and rank the top complaint topics"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Pangolinfo Review Mining MCP
A differentiated, review-mining-only MCP server for Amazon product reviews. It mines what buyers complain about, how sentiment trends, and which complaint themes dominate — it does not duplicate the general Pangolinfo Amazon Data MCP.
How it differs from the general Amazon Data MCP
General Amazon Data MCP | This Review Mining MCP | |
Scope | 19+ tools: product search, product detail, best sellers, new releases, sellers, categories, niches, WIPO, SERP, Alexa | 5 tools, reviews only |
Intent | General Amazon commerce intelligence | Review mining: complaints, sentiment, complaint topics |
Analysis | Returns raw data | Local analysis on top of fetched reviews (keyword-theme tagging, distribution, monthly trend, combined report) |
Upstream | Hosted Pangolinfo MCP server | Same hosted server's |
If you need product search or anything beyond reviews, use the general MCP. If you need to know what buyers complain about and how that changes over time, use this one.
Related MCP server: Pangolinfo Amazon Reviews MCP
Architecture
MCP client (Claude Code, Cursor, Codex, ...)
└─ stdio ─► this server (src/index.ts)
└─ Streamable HTTP MCP client ─► https://mcp.pangolinfo.com/mcp
└─ upstream tool: get_amazon_reviews
└─ local analysis (src/analysis.ts): tagging, sentiment, topicsThe server is a bridge plus analysis. It stores no API key and no
review data; the key is sent only as an Authorization: Bearer header
to the hosted server, taken from the environment.
Why a bridge instead of direct REST calls: the Pangolinfo docs page for
the Review API lists parameters and response fields, but its request-URL
and example blocks did not survive text extraction, so the direct REST
endpoint is unconfirmed and deliberately not hardcoded here. The
bridge path uses only confirmed facts: the hosted endpoint
(https://mcp.pangolinfo.com/mcp, from the official amazon-data-mcp
README) and the upstream get_amazon_reviews tool name + input schema
(confirmed live via tools/list on 2026-10-26, a free metadata call).
See TODOs below for the direct-REST follow-up.
Setup
Requirements: Node.js 18 or newer (developed/tested on Node 24).
npm install
npm run buildRun (live mode):
export PANGOLINFO_API_KEY="your-key-here" # never commit a real key
node dist/src/index.jsWithout a key the server still starts and answers initialize and tools/list; live tool calls fail with a clear message until PANGOLINFO_API_KEY is set.
Run (mock mode, no network, no key — for tests and demos):
PANGOLINFO_REVIEW_MINING_MOCK=1 node dist/src/index.jsMCP client configuration (example, Claude Code style):
{
"mcpServers": {
"pangolinfo-review-mining": {
"command": "node",
"args": ["/absolute/path/to/pangolinfo-review-mining-mcp/dist/src/index.js"],
"env": { "PANGOLINFO_API_KEY": "your-key-here" }
}
}
}Environment variables:
Variable | Required | Purpose |
| Yes (live mode) | Bearer token for the hosted Pangolinfo MCP server |
| No | Upstream MCP endpoint; default |
| No |
|
Tools (5, all review-mining only)
Tool | What it does | Key inputs |
| Paginated review fetch for one ASIN, with billing ( |
|
| Complaint signals from negative ( |
|
| Rating distribution, average star, negative/critical/positive shares, monthly trend |
|
| Ranked complaint themes with counts, shares, example titles |
|
| Combined per-ASIN summary: totals, sentiment, top topics, most-endorsed complaints, billing; cites the Oct 12 baseline for B0FQFB8FMG as historical reference only |
|
Complaint themes (English keyword heuristic, v1 — transparent, not a
classifier): quality_defect, battery_power, connectivity,
comfort_fit, sound_quality, shipping_delivery, returns_refunds,
value_price, authenticity, app_software. Every match reports the
keyword that fired.
Marketplaces (site): amz_us (default), amz_de, amz_uk, amz_jp,
amz_fr, amz_it, amz_es, amz_br, amz_au, amz_mx, amz_in,
amz_eg, amz_ae, amz_ca.
Billing
The Review API is documented at 5 credits/page (docs "积点消耗: 5个/次" and per-page billing in
bizContext.pageCount), and a measured Oct 2026get_amazon_reviewscall returnedpointCost: 5for one page.Discrepancy flagged: the upstream MCP tool description currently states 10 credits/page. This server does not resolve that discrepancy by assertion — every tool reports
pointCostexactly as returned by the upstream response, and the billing note in each response names both figures.Free tier: 60 credits/month, recurring. At the measured 5/page rate that covers ~12 review pages/month; budget
pageCountaccordingly.review_mining_reportmakes two upstream fetches (all_stars + critical), so it costs twice one fetch.The stored Pangolinfo API key expired (measured 2026-10-24). Live end-to-end testing is pending on the key being reconnected; see TEST_REPORT.md.
Tests
npm test # builds, then runs node --test on dist/test/17 tests, all passing at build time (see TEST_REPORT.md): analysis
unit tests, tool-handler tests against the mocked upstream, the Oct 12
baseline fixture test, and a stdio smoke test that spawns the real
server in mock mode and speaks MCP JSON-RPC to it. All test review
data is mocked (synthetic authors "Mock Reviewer A" …); the only real
measured numbers in the repo are the aggregate baseline in
fixtures/airpods-pro-3-baseline.json (4,268 total / 1,392 negative
reviews for ASIN B0FQFB8FMG, measured 2026-10-12, reference only).
Limitations (read before presenting results as fact)
Complaint tagging is an English keyword heuristic, not sentiment ML. Non-English reviews will under-match until lexicons for their languages are added.
Star values come from strings like "5.0 out of 5 stars"; unparseable stars fall into
unknownand are excluded from averages.Dates come from strings like "October 14, 2026"; unparseable dates fall into the
unknownmonthly bucket.totalReviewsis returned by upstream as a string and may be empty when unavailable; it is passed through, not computed.review_mining_reportfetches all_stars + critical, so its review counts are per-fetch, not a single de-duplicated sample.
Publication status (2026-10-26)
mcprush accepts MCP servers or agent skills only (verified 2026-10-26:
its server wizard requires a repo / npm / PyPI / container / hosted MCP
endpoint and passes initialize + tools/list verification).
GitHub repo: live at https://github.com/Pangolin-spg/pangolinfo-review-mining-mcp
npm package:
pangolinfo-review-mining-mcp0.1.1, published 2026-10-26 (0.1.0 was the first publish the same day; 0.1.1 adds themcpNamefield required by the MCP Registry)mcprush listing: submitted 2026-10-26, in review (expected URL: https://mcprush.com/pangolin-spg/pangolinfo-review-mining-mcp)
Server-card info needed: name, one-line description, and a paragraph of at least 120 characters on what it does and who it is for.
Pricing: free plan (or priced plans with name, monthly price, call allowance); review takes up to two working days.
No video/intro URL field was visible in the submission form's expanded steps during the read-only check; if one appears, the project's intro videos are the Pangolinfo EN/ZH videos on file.
Backlink rule (standing): any link back to pangolinfo.com content in a listing must carry
?utm_source=<platform>&utm_medium=referral(plusutm_content=<product>when one platform carries several products) for GA4 referral attribution.
TODOs / unconfirmed items
Direct REST endpoint (unconfirmed): the docs page's request-URL and example blocks did not extract, and no workspace file records the Review API's REST URL. The bridge design avoids needing it, but a direct-REST mode should not be added until the URL is confirmed from docs or a measured call.
Live end-to-end test (done 2026-10-26): verified with a temporary 7-day key:
get_product_reviews+mine_complaintson ASIN B0FQFB8FMG, 5 credits/page each, 4,446 total reviews / 1,457 critical at time of test.Billing discrepancy (resolved 2026-10-26): live
pointCost= 5/page; the upstream tool description's 10/page is stale.Publish (done 2026-10-26): GitHub repo live, npm 0.1.0 published, mcprush listing submitted (in review).
Available Tools
5 toolsget_product_reviewsB
Fetch paginated Amazon product reviews for one ASIN via Pangolinfo, with the upstream billing (pointCost) reported verbatim. Billing: docs and measured calls show 5 credits/page; the upstream tool description currently states 10 credits/page — this tool reports pointCost as returned, it does not assert a rate.
Inputs: asin (required), site, sortBy, mediaType, +2 more.
mine_complaintsB
Extract complaint signals from negative (critical, 1-3 star) reviews for one ASIN. Tags each complaint review with human-readable themes (quality_defect, battery_power, connectivity, comfort_fit, sound_quality, shipping_delivery, returns_refunds, value_price, authenticity, app_software) using a transparent English keyword heuristic — not a classifier. Optionally filter to complaints with at least minHelpful helpful votes.
Inputs: asin (required), site, pageCount, minHelpful.
review_mining_reportA
Combined per-ASIN review-mining summary: totals, rating distribution, monthly trend, top complaint topics, most-endorsed complaints, and billing as returned. When the ASIN matches the documented Oct 12, 2026 baseline (B0FQFB8FMG), the report also cites that historical baseline for reference, clearly labeled as historical — never as current data.
Inputs: asin (required), site, pageCount.
review_sentiment_summaryB
Rating distribution, average star, negative/critical/positive shares, and a monthly sentiment trend for one ASIN's reviews. Pure local computation over fetched reviews.
Inputs: asin (required), site, pageCount.
top_complaint_topicsB
Ranked complaint themes across negative reviews for one ASIN, with counts, shares, and example review titles for traceability.
Inputs: asin (required), site, topN, pageCount.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
get_product_reviews (raw fetch) and review_sentiment_summary (local computation) are cleanly separable, but mine_complaints and top_complaint_topics both operate on complaint themes from negative reviews and differ mainly in granularity (per-review tagging vs. ranked aggregation), which invites misselection. review_mining_report is explicitly a superset of rating distribution + top complaint topics, so it overlaps with two other tools even though the descriptions flag the combined nature.
Two names use verbs (get_product_reviews, mine_complaints) while three are noun phrases (review_mining_report, review_sentiment_summary, top_complaint_topics). The vocabulary is coherent and readable, but there is no predictable verb_noun pattern across the set.
Five tools is well within the sensible range for a focused review-mining server. There is mild redundancy because the combined report duplicates outputs available from the sentiment and complaint-topic tools, but every tool still has a defensible role.
The surface covers the full review-mining lifecycle for a single ASIN: raw paginated fetch, sentiment/trend, per-review complaint tagging, ranked complaint topics, and a consolidated report. Minor gaps remain (no ASIN/product discovery or cross-ASIN comparison), but an agent with a known ASIN can complete the workflow without dead ends.
Maintenance
Related MCP Connectors
Walmart & Amazon review insights: complaints, topic sentiment, new-review alerts. Pay per result.
Live Amazon product, review, search, deal, offer/stock and seller data across 23 marketplaces.
Analyze product reviews: pain points, feature requests, sentiment and competitive gaps for sellers.
Amazon keyword volume, reverse-ASIN, and SERP data across 11 marketplaces.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides read-only access to normalized Amazon marketplace data, including product details, search, offers, reviews, sellers, categories, deals, best sellers, identifiers, stock, and sales estimates across 13 marketplaces.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to research Amazon reviews and voice-of-customer signals through read-only tools for paginated reviews, complaint evidence, rating summaries, media filtering, and side-by-side comparisons of two products.522 npmMIT
- AlicenseAqualityBmaintenanceLive Amazon marketplace data for AI agents: product details, prices, reviews, keyword search, best-sellers, deals, offers and stock, and seller profiles across 20 marketplaces.121MIT
- AlicenseAqualityBmaintenanceMines public App Store and Steam reviews to surface the complaints, rating drops per version, and common pain points across one app or a set of competitors, with no API keys required. Enables natural-language comparison of up to eight apps or games by country and category so users can spot product opportunities and gaps.432 PyPIMIT