If you're running a TikTok Shop brand or evaluating creator commerce opportunities, this connects Claude to Return on Creators benchmark data spanning 100+ brands and $20M+ in processed GMV. You get eight tools covering category benchmarks (median GMV, AOV, engagement rates), ROC projection calculators with vertical-specific coefficients, creator profile matching, content format rankings, commission guidance, brand fit scoring, shop readiness assessments, and amplifier program gap analysis. Supports beauty, CPG, fashion, wellness, home, and supplements categories. Responses include confidence levels and cite specific data sources like the syncly TikTok Affiliate Playbook and 360om commission benchmarks. Useful when you need actual numbers to size creator programs or justify TikTok Shop investment.
Creator commerce intelligence for TikTok Shop brands — powered by Return on Creators.
Built on the Model Context Protocol, this server gives AI assistants real benchmark data from 100+ TikTok Shop brands and $20M+ GMV processed.
| Tool | Description |
|---|---|
roc_get_category_benchmarks | Median + top-quartile GMV, AOV, creator activation rates, and top content formats by category |
roc_calculate_projected_roc | Calculate projected Return on Creators multiple with vertical-specific coefficients |
roc_get_creator_profile | Ideal creator tier, engagement benchmarks, match scoring rubric, and recruitment targets |
roc_get_content_formats | Highest-converting TikTok content formats ranked by GMV contribution |
roc_get_commission_guidance | Market-rate commission guidance with tiered structure and sample strategy |
roc_analyze_brand_fit | Full brand fit analysis — fit score, blockers, expected GMV range |
roc_get_tiktok_shop_readiness | Readiness score with prioritized action plan for TikTok Shop launch |
roc_get_amplifier_fit | Creator program gap analysis — constraints, projections, weekly priority actions |
beauty · cpg · fashion · wellness · home · supplements
npm install
npm start
# Server runs at http://localhost:3000/mcp
TRANSPORT=stdio npm start
PORT=8080 npm start
Add to your claude_desktop_config.json:
{
"mcpServers": {
"roc": {
"command": "node",
"args": ["/absolute/path/to/roc-mcp-server/src/index.js"],
"env": { "TRANSPORT": "stdio" }
}
}
}
Use any MCP client that supports Streamable HTTP transport:
http://localhost:3000/mcp
Every tool response includes:
{
"result": { ... },
"confidence": "high",
"dataSource": "RoC platform data — 100+ brands, $20M+ GMV processed",
"dataAsOf": "2026-Q1",
"disclaimer": "Estimates based on RoC platform benchmarks. Actual results vary by brand, execution quality, and market conditions."
}
Benchmarks sourced from:
Data as of: 2026-Q1
MIT
mcp-name: io.github.sugar-co-dev/roc-mcp-server
io.github.shelvick/shopify-subscription-reconciliation
zleventer/google-ads-mcp
csoai-org/meok-stripe-acp-checkout-mcp
io.github.mharnett/google-ads
csoai-org/stripe-billing-mcp
co.pipeboard/google-ads-mcp