Intelligent report management with semantic search. Find insights across all your analyses, share results instantly, and build knowledge from every statistical run.
Watch how AI assistants search, retrieve, and share statistical insights with semantic understanding
AI-powered search understands context and meaning, not just keywords. Find related analyses instantly.
Generate secure, time-limited URLs for any report. No login required for viewers.
Every analysis is automatically saved and searchable. Build knowledge over time.
Three simple steps to find, analyze, and share insights
Use semantic search to find reports by meaning, not just keywords. Ask questions like "regression analyses from last month" or "customer behavior studies with high R²".
mcp.reports.search( semantic_query="sales forecasting models with seasonal patterns", threshold=0.7 )
Fetch complete report data including metrics, visualizations, datasets, and AI insights. Access specific sections or get everything at once.
mcp.reports.search( job_ids=["mcp_arima_forecast_xyz"], include_data=true, keys=["predictions", "seasonal_components"] )
Generate secure, shareable URLs that work in any browser. Set expiration times and access limits for controlled sharing.
mcp.reports.view( processing_id="mcp_arima_forecast_xyz", expires_in=86400 // 24 hours )
Find exactly what you need with advanced filtering and AI-powered search
Find reports by meaning and context, not just exact matches.
Combine multiple filters for precise results.
Retrieve specific parts of reports efficiently.
Work with multiple reports simultaneously.
See which sections matched your search.
Zero-friction report viewing and sharing.
Real-world examples of finding and using reports
mcp.reports.search( semantic_query="high R-squared regression models", date_from="2025-01-01", tool_names=["linear_regression", "ridge_regression"], limit=10 )
Returns regression analyses with strong performance metrics from this year.
mcp.reports.search( semantic_query="time series forecasting with seasonal decomposition for retail sales", threshold=0.8, // High similarity only sort_by="similarity" )
Finds highly relevant time series analyses with seasonal patterns for retail.
// First, find the report results = mcp.reports.search(semantic_query="customer lifetime value") // Then fetch specific sections mcp.reports.search( job_ids=[results[0].id], include_data=true, keys=["feature_importance", "predictions", "model_metrics"] )
Two-step process: search first, then retrieve only the data you need.
// Generate a week-long shareable link mcp.reports.view( processing_id="mcp_ridge_regression_quarterly", expires_in=604800, // 7 days max_access_count=100 // Limit views ) // Returns: https://api.mcpanalytics.ai/rpt/rpt_ABC123
Perfect for sharing quarterly reports with stakeholders.
Comprehensive analysis results with everything you need
Residual plots, Q-Q plots, feature importance charts, time series decompositions, and more.
R², RMSE, MAE, p-values, confidence intervals, AIC/BIC, and all relevant statistics.
Business-friendly interpretations with actionable recommendations and key findings.
Predictions, residuals, coefficients, and processed datasets ready for further analysis.
Assumption validation, outlier detection, multicollinearity checks, and model diagnostics.
Complete documentation of methods, parameters, and data transformations applied.
Every analysis becomes searchable, shareable knowledge. Never lose insights again.