Pangolinfo Review Mining MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PANGOLINFO_API_KEY | No | Bearer token for the hosted Pangolinfo MCP server. Required in live mode. | |
| PANGOLINFO_MCP_URL | No | Upstream MCP endpoint; default is https://mcp.pangolinfo.com/mcp. | https://mcp.pangolinfo.com/mcp |
| PANGOLINFO_REVIEW_MINING_MOCK | No | Set to 1 to enable mock mode (mocked reviews, no network, no API key required). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_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. |
| 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. |
| 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. |
| top_complaint_topicsB | Ranked complaint themes across negative reviews for one ASIN, with counts, shares, and example review titles for traceability. |
| 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.