KongMing Growth MCP

io.github.kongming-aiPublished by GitHub account kongming-aiv1.0.4Updated Oct 30, 2026

Cross-border growth tools: mentions, pain points, competitors, GEO, synthesis, AI media.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

KongMing Growth MCP is a remote server giving assistants cross-border e-commerce growth data: customer mentions, pain points, competitor comparisons and…

What you can do
  • Query multi-channel customer mentions with sources and sample sizes, and cluster pain points by severity
  • Track sentiment trends over time
  • Query competitor mentions and build brand-versus-competitor comparison matrices
  • Check AI-engine visibility per query (GEO) and pull self-contained AI-visibility audit snapshots
  • Generate a seven-layer, evidence-backed strategic synthesis
  • Search your own knowledge base semantically and read the model catalog; a media pricing quote tool is marked coming soon
When to use it
Useful for DTC brands selling on Amazon or independent sites that want an assistant to answer questions about customer complaints, competitor positioning or AI-search visibility, with sources and time windows attached.
Requirements
A remote Streamable HTTP endpoint; no local install. An API key issued by KongMing staff (requested by email) sent as an Authorization Bearer header. Usage is billed in credits with per-key caps.
Before you install
Requires an API key sent in the Authorization header, and keys are issued and scoped by the vendor's staff. Usage draws on paid credits with per-key caps, so calls can cost money. Queries and knowledge-base searches are sent to a third-party service.

Installation

In SourceWeft

  1. Open KongMing Growth MCP in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.kongming-ai%2Fmcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "kongming-growth": {
      "type": "http",
      "url": "https://mcp.kmingai.com/mcp"
    }
  }
}

README

KongMing 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):

ToolAnswers
query_mentionsMulti-channel customer mentions with sources & sample sizes
get_pain_pointsPain-point clustering, severity-ranked
get_sentiment_trendSentiment trend over time
query_competitor_mentionsCompetitor mention queries
compare_competitorsBrand-vs-competitor comparison matrix
query_geo_visibilityAI-engine visibility per query (GEO)
get_geo_audit_snapshotSelf-contained AI-visibility audit snapshot
generate_strategic_synthesis7-layer strategic synthesis, evidence-backed
search_knowledgeSemantic search over your knowledge base
model_catalog_getModel catalog (credits language)
media_estimate_priceMedia pricing quote (coming soon)

Every answer carries sources, sample sizes and time windows. Zero fabrication — insufficient data is stated as insufficient.

Quickstart

  1. Request an API key: email [email protected] — keys are issued and scoped by KongMing staff.
  2. 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).
  3. 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-user benefits are as shown on the activation page.

Docs

Status

  • Public endpoint live
  • 20/20 catalog tools callable (media family granted 2026-10-30)
  • Error codes -32008/-32009 activation (with E4 billing window)
  • Listed on the official MCP Registry (io.github.kongming-ai/mcp-server)
  • Marketplace listings (WorkBuddy / Doubao / Coze) in review pipeline

© KongMing AI — www.kmingai.com

Source: README.md at commit 556bb98

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v1.0.4LatestOct 30, 2026
  2. v1.0.1Sep 26, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.