FlowCay logo
FlowCay
Amazon Sorftime Research MCP Skill

Amazon Sorftime Research MCP Skill

Amazon product research Agent Skill with listing audits, category/keyword/review analysis, integrating Sorftime and seller-tool MCPs.

Install command

npx skills add https://github.com/liangdabiao/amazon-sorftime-research-MCP-skill
SkillOpen SourceAmazon
Added on Popularity 3

Details

Overview

The Amazon Sorftime Research MCP Skill (amazon-sorftime-research-mcp-skill) is an open-source agent skill that turns AI coding agents (Claude Code, Codex, Cursor, etc.) into full-time Amazon product researchers. It wires up MCP (Model Context Protocol) servers for Sorftime, Sif, Xiyou (西柚洞察) and SellerSprite (卖家精灵) data services and ships nine ready-to-use skills covering competitor analysis, category selection, keyword research, review mining, deep product research, traffic/ad diagnostics and listing building — with reports output as Markdown, CSV and HTML.

Key Features

  • Nine core skills for cross-border e-commerce decision-making, invoked with slash commands such as /amazon-analyse, /category-select, /keyword-research, /review-analysis, /product-research, /sif-amazon-research, /xiyou-insight, /sellersprite-amazon-research and /amazon-listing-builder.
  • Single Listing Analysis (amazon-analyse): full-dimension teardown of any ASIN across 14 Amazon marketplaces — product details, sales/price/BSR trends, reviews, traffic-driving keywords and competitor keyword layout.
  • Category Selection (category-select): Top-100 market analysis with five-dimension scoring to rank and pick profitable categories.
  • Keyword Research (keyword-research): collects 1,500+ keywords via the Sorftime API and classifies them into 8 dimensions (negative, brand, material, scenario, attribute, function, core, other) with ad-strategy guidance — negative-keyword lists, exact-match groups, scenario and broad-match ad groups.
  • Review Analysis (review-analysis): 6-dimension pain-point clustering of buyer reviews with service-risk warnings and product-improvement suggestions.
  • SellerSprite full-chain research: 43 MCP tools and 10 workflows — product selection, market overview, competitor teardown, keyword mining, listing optimization, traffic source analysis, blue-ocean opportunity finding (ABA trends + Google Trends), review NLP insights, pricing strategy and ad optimization.
  • Xiyou Insight: 7 scenario workflows for ad monitoring, traffic gaps, competitor breakdown, new-product launch, ad-budget transparency and keyword-database building.
  • Listing Builder (amazon-listing-builder): an 8-step, evidence-driven workflow ("analyze first, generate next, validate last") that builds listings around Cosmo semantics + Alexa/Rufus conversational shopping trends — layered keyword library, buyer-question library, evidence library, title/bullet/A+/Search Terms/QA drafts, plus a 4-point compliance & semantic audit.
  • Cross-platform data: Amazon (14 sites), TikTok Shop (6 sites), Walmart US, Shopee (8 sites), Temu US/EU and 1688 sourcing supply data.

How to Use

  1. Use a Skill-compatible agent such as Claude Code, Cursor, or Codex.
  2. Install from the terminal (Node.js required):
npx skills add https://github.com/liangdabiao/amazon-sorftime-research-MCP-skill

Or paste the install prompt from this tool page into your agent and ask it to install for you. 3. Restart / reload the agent so the new Skill is loaded. 4. Invoke the Skill with its slash commands or by asking the agent to run the workflow described in Overview / Key Features. 5. Review outputs before publishing — treat model-generated copy, images, and data as drafts.

Pricing

  • Free & open source: the skill itself (MIT-style usage via GitHub) is free — you install it into Claude Code, Codex or similar agents.
  • Paid part — MCP data subscriptions: you need active accounts/keys for the underlying data services. Sorftime MCP service is activated after login at Sorftime Enterprise Solutions (key: mcp.sorftime.com?key=YOUR_KEY) and requires a purchased/active Sorftime plan. SellerSprite, Sif and Xiyou keys are likewise provided by their own paid subscriptions.

Best For

Amazon sellers and cross-border e-commerce operators who use AI coding agents (Claude Code, Codex, Cursor) and want automated, LLM-driven competitor research, keyword mining, category selection, review analysis and listing optimization — especially brands scaling to 14+ marketplaces.

FAQ

What do I need to run it?

An AI agent that supports Claude-style skills (Claude Code, Codex, Openclaw, etc.), a Sorftime MCP API key (plus optional Sif / Xiyou / SellerSprite keys), and Python tooling included in the repo.

Does it need coding skills?

No — commands are slash-based (/amazon-analyse, /keyword-research, etc.). The agent fetches data via MCP and writes structured reports automatically.

Which marketplaces are covered?

Amazon (14 sites), TikTok Shop (6 sites), Walmart US, Shopee (8 sites), Temu US/EU, plus 1688 for sourcing cost comparison.

What do the report outputs look like?

Markdown reports (listing_package.md, keyword_library.md, audit_report.md, etc.), CSV keyword libraries and HTML dashboards, saved to a local reports directory.

Is the skill itself free?

Yes, it's open source on GitHub. You only pay for the underlying data-service subscriptions (Sorftime, SellerSprite, Sif, Xiyou) that supply the MCP data.