Roc Mcp Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Roc Mcp Server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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/mcpTRANSPORT=stdio npm startPORT=8080 npm startAdd 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/mcpEvery 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
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.