Insights
The Missing Layer
Introducing Introspective Context Engineering — a method for building Rich Domain MCP Servers where the AI doesn't just query your data, it understands what it means. Based on multiple MCP servers running on real production business data.
Read the Practitioner ReportEnterprise AI Without an Enterprise Budget
Nine production MCP servers, no platform team, no framework dependencies, no API bill. The architecture that puts enterprise AI inside a mid-market budget.
MCP Is the AI Platform
Nine production MCP servers, one mid-sized firm. No agent framework, no RAG pipeline, no AI-platform vendor. MCP plus enterprise identity is the whole stack.
Six Things the MCP Spec Should Fix
Six fixes the MCP spec needs after 52 tools and nine APIs in production: from Resources no client surfaces to enums that break agent reasoning.
Your MCP Server Should Get Smarter Every Week
Three calls to the same tool with tightening filters. Without queryIntent: opaque retries. With it: the exact metadata gap, fixable in minutes.
97% of MCP Tool Descriptions Are Broken
856 tools, 103 servers, 97.1% with at least one smell. After shipping 52 tools across 7 production MCP servers, here's the eight-block pattern that fixed ours.
The Six Levels of MCP Servers
Seven production MCP servers, nine APIs, 52 tools later: a six-level maturity ladder from hollow API wrappers to apps that write back. Where does yours sit?
Your Data Is Fine. Your AI Doesn't Know What It Means.
Enterprise AI pilots fail 80% of the time. Surveys blame data quality. After seven production MCP servers, the real problem was almost never the data.
Production MCP: A Practitioner's Guide
Nine production MCP servers at one mid-market firm. The complete framework: from understanding data through identity-bound deployment, end to end.