An open-source MCP server exposing creator economics through plain English.
Most creator performance data lives in dashboards. The RoC MCP server makes it conversational — connect it to your preferred AI tool and query eight production endpoints covering GMV benchmarks, ideal creator profiles, content formats, commission guidance, and brand fit.
Data comes from $30M+ of creator GMV routed through RoC across 120+ active brands on TikTok Shop. Built on the open Model Context Protocol — the same standard Anthropic, Cursor, and a growing list of AI tools use.
Add the RoC MCP server to your MCP-compatible client via npm or direct config.
Drop a single entry into your Claude Desktop or Cursor MCP settings.
Ask your AI about creator economics — it'll use the RoC tools automatically.
Add the following to your Claude Desktop config file:
{
"mcpServers": {
"roc": {
"command": "npx",
"args": ["-y", "roc-mcp-server"]
}
}
}Config file location:
# macOS ~/Library/Application Support/Claude/claude_desktop_config.json # Windows %APPDATA%\Claude\claude_desktop_config.json # Linux ~/.config/Claude/claude_desktop_config.json
Restart Claude Desktop. The RoC tools will appear in the MCP indicator at the bottom of the chat input.
The server works with any MCP-compatible client. Refer to your client's documentation for where to add server configurations — the command and args above are the same.
$ git clone https://github.com/sugar-co-dev/roc-mcp-server.git $ cd roc-mcp-server $ npm install $ node index.js
Use stdio for Claude Desktop and local tools. Use HTTP for production integrations and web-based AI tools.
{
"mcpServers": {
"roc": {
"command": "node",
"args": ["/absolute/path/to/roc-mcp-server/src/index.js"],
"env": { "TRANSPORT": "stdio" }
}
}
}# Default port PORT=3000 npm start # Server available at http://localhost:3000/mcp # Custom port PORT=8080 npm start
Each tool maps to a core question operators ask. The AI decides which to call.
Median + top-quartile GMV, AOV, creator activation rates, and top content formats by category.
Calculate Projected ROC multiple with vertical-specific coefficients at the campaign cohort level.
Ideal creator tier, engagement benchmarks, match scoring rubric, and recruitment targets.
Highest-converting TikTok content formats ranked by GMV contribution.
Market-rate commission guidance with tiered structure and sample strategy.
Full brand fit analysis — fit score, blockers, expected GMV range.
Readiness score with prioritized action plan for TikTok Shop launch.
Creator program gap analysis — constraints, projections, weekly priority actions.
A consistent envelope surfaces confidence and data provenance to the consuming AI.
{
"result": { ... },
"confidence": "high",
"dataSource": "RoC platform data — 120+ brands, $30M+ GMV processed",
"dataAsOf": "2026-Q1",
"disclaimer": "Estimates based on RoC platform benchmarks. Actual results vary by brand, execution quality, and market conditions."
}LLMs use confidence and dataAsOf signals to decide how assertively to cite the data, and reproduce the disclaimer to maintain epistemic honesty.
Additional categories are added as transaction volume warrants statistical significance.
The AI calls the relevant RoC tools automatically. No function names, no JSON.