Blog
Semantic layers, agentic analytics, and shipping governed data to AI agents.
MCP ChartsViews and embed mode: two new ways to use MCP ChartsYour MCP server can now return a whole dashboard from one tool call, and render the same chart inside your own admin console. What shipped in @bonnard/mcp-charts since the visualize tool.Semantic LayerThe Semantic Layer You Already HaveBefore adopting Cube.dev or a custom semantic layer, use your warehouse's native metadata (comments, keys, enums, stats) as a lightweight one for agents.MCP ChartsMCP Charts: Add Interactive Charts to Your MCP ServerGive your AI agent a visualize tool: interactive charts inside any MCP Apps client from real query data. Works with any MCP server via @bonnard/mcp-charts.MCP ChartsHow Bonnard Builds Agent-Friendly MCPsExposing data over MCP is easy. Designing a tool an agent uses well is hard. Discovery-first tools, compact responses, instructive errors, determinism.Agentic AnalyticsAI Data Analysis: Why Governed Metrics Beat Raw SQLA guide to AI data analysis for SaaS: the tool categories, the accuracy problem, and the MCP-native way to chart query results inside an agent.Agentic AnalyticsAI Reporting: How to Automate Reports Without Losing TrustA guide to AI reporting for SaaS: the tool landscape, the trust problem, and the MCP-native way to render charts from your query results inside an agent.AnalyticsAnalytics API: How to Serve Governed Metrics to Any ConsumerAn analytics API exposes your metrics programmatically. How to build one that serves dashboards, AI agents, and integrations from the same definitions.AnalyticsBest Embedded Analytics Tools for SaaS in 2026Comparing the best embedded analytics tools for B2B SaaS in 2026: Metabase, Explo, Luzmo, GoodData, Looker, and the MCP-native option for AI agents.AnalyticsHow to Build Customer-Facing Analytics for B2B SaaSA guide to customer-facing analytics 2026 for B2B SaaS: the options, the tradeoffs, and the MCP-native way to put interactive charts inside an AI agent.AnalyticsKPI Dashboards Are Broken. Here's What Replaces Them.KPI dashboards show stale numbers nobody trusts. Governed metrics through a semantic layer give every consumer the same live data, dashboards to AI agents.AnalyticsReal-Time Analytics: When You Need It and When You Don'tNot every metric needs real-time data. Here's how to decide what needs sub-second freshness, what can be cached, and how pre-aggregation handles both.Semantic LayerSelf-Service BI Is a Lie (Unless You Govern the Metrics)Self-service BI for customers promised to free the data team. Instead it created metric chaos. The category, the tradeoffs, and where AI agent charts fit.Semantic LayerWhat Is a Semantic Layer? Guide for Data EngineersA semantic layer defines business metrics once so every consumer gets the same answer, including AI agents. How it works, with code examples.Agentic AnalyticsWhat Is an Agentic Semantic Layer?An agentic semantic layer is a metrics layer built for AI agents: business logic defined once, exposed via MCP or API, queried as governed definitions.Agentic AnalyticsWhy Your AI Agents Need a Semantic LayerWhy AI agents need a semantic layer: raw SQL produces inconsistent, ungoverned results. What goes wrong without one, and how governed metrics change it.Agentic AnalyticsHow to Connect an AI Agent to Your Data WarehouseConnect an AI agent to your data warehouse: expose governed metrics over MCP, query without raw SQL, and chart the result in Claude or ChatGPT.