A DBA of PeopleDrivenAI LLC
Adhoc analysis generation — your data, your question, a custom analysis on demand.
⚠️ Beta — v2 rebuild in progress. mcpanalytics.ai is live behind a beta banner while we ship v2. Some features are incomplete or unstable during this period. Tracking: #22 — what's changing, what to expect. Prefer to wait? Get launch updates →
MCP Analytics is an AI-native analytics company. You bring data and a question; a standing team of specialist agents builds a custom analysis module specific to your data, validates the methodology, and ships back a citable, interactive report. Every commissioned module is yours — it lives in your library, reruns on fresh data for a fraction of the creation cost, and is queryable from Claude, Cursor, or any MCP client. The work compounds.
The mental model is hire the team, not "use the tool."
- Custom module creation — describe what you want analyzed; the pipeline builds a module specific to your data and domain. Pay once, own it, rerun forever.
- Cornerstone modules — pre-built analyses (t-tests, regression, churn, segmentation, forecasting, customer LTV, A/B testing, time series, survival analysis, more) that prove the team can build things that work
- Live connectors — Google Analytics 4, Google Search Console, Shopify, Stripe (more coming)
- Citable, sourceable, reproducible reports — APA/MLA/Chicago/BibTeX, embedded R source code, fixed seeds, Docker isolation
- MCP-native — query your library from Claude, Cursor, Windsurf, or any MCP client
- Secure — OAuth2, encryption at rest, isolated container processing per analysis
- Languages: Python, R, TypeScript
- Frameworks: FastAPI, Docker, MCP Protocol
- Database: PostgreSQL
- Security: OAuth2, JWT, end-to-end encryption
- Issues & Feature Requests — report bugs, request analysis modules or connectors
- Discussions — questions, ideas, show & tell
- Roadmap — what's planned
- Website: mcpanalytics.ai
- Email: support@mcpanalytics.ai
© 2026 PeopleDrivenAI LLC