About KongMing Growth MCP
KongMing Growth MCP provides cross-border DTC brands with analysis of customer mentions, pain points, competitors, and GEO visibility. Its sourced findings include sample sizes and time windows, alongside strategic synthesis for growth decisions.
Key features
- 01Multi-channel mention queries
- 02Severity-ranked pain-point clusters
- 03Sentiment trend analysis
- 04Competitor comparison matrices
- 05GEO visibility audits
- 06Evidence-backed strategic synthesis
Use cases
- 01Find recent customer complaints
- 02Compare brand and competitor mentions
- 03Check AI-engine visibility
- 04Synthesize data for growth planning
MCP support
It provides 11 cross-border commerce data and analysis tools through a Streamable HTTP MCP server; 10 tools are currently open to compatible clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.kmingai.com/mcpclaude mcp add --transport http kongming-ai https://mcp.kmingai.com/mcp{"mcpServers":{"kongming-ai":{"type":"http","url":"https://mcp.kmingai.com/mcp"}}}Open in Cursor{"servers":{"kongming-ai":{"type":"http","url":"https://mcp.kmingai.com/mcp"}}}Open in VS Code{"mcpServers":{"kongming-ai":{"type":"http","url":"https://mcp.kmingai.com/mcp"}}}{"mcpServers":{"kongming-ai":{"serverUrl":"https://mcp.kmingai.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.kmingai.com/mcpAuth requiredTools
Details
From the project READMEKongMing Growth MCP
Cross-border e-commerce growth data & analysis over MCP (Model Context Protocol).
Endpoint: https://mcp.kmingai.com/mcp · Transport: Streamable HTTP · Auth: Authorization: Bearer <key>
Live since 2026-09-26. Mainland-China direct: 5/5 reachable, 628ms avg.
What you get
11 tools for DTC brands selling cross-border (Amazon / independent sites):
| Tool | Answers |
|---|---|
| query_mentions | Multi-channel customer mentions with sources & sample sizes |
| get_pain_points | Pain-point clustering, severity-ranked |
| get_sentiment_trend | Sentiment trend over time |
| query_competitor_mentions | Competitor mention queries |
| compare_competitors | Brand-vs-competitor comparison matrix |
| query_geo_visibility | AI-engine visibility per query (GEO) |
| get_geo_audit_snapshot | Self-contained AI-visibility audit snapshot |
| generate_strategic_synthesis | 7-layer strategic synthesis, evidence-backed |
| search_knowledge | Semantic search over your knowledge base |
| model_catalog_get | Model catalog (credits language) |
| media_estimate_price | Media pricing quote (coming soon) |
Every answer carries sources, sample sizes and time windows. Zero fabrication — insufficient data is stated as insufficient.
Quickstart
- Get an API key: app.kmingai.com → Settings → Developer → Create API Key.
- Point any MCP client at the endpoint with your key as a Bearer header — see docs/quickstart.md for per-client guides (Doubao Work, Tencent WorkBuddy, generic EN).
- Ask: "What are my customers complaining about in the last 30 days?"
Billing
Credits — same price as the KongMing workspace, no markup for external shells. Per-key usage caps. New accounts include trial credits.
Docs
Status
- Public endpoint live
- 10/11 tools open (media pricing quote coming soon)
- Error codes -32008/-32009 activation (with E4 billing window)
- Marketplace listings (WorkBuddy / Doubao / Coze) in review pipeline
© KongMing AI — www.kmingai.com
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.