Founder · Author · Maintainer
Model Context Protocol (MCP) server that gives AI agents secure, structured access to Microsoft Dataverse — schema, metadata, data, and platform operations through the Dataverse Web API.
- Designed and shipped a production-grade MCP server in TypeScript exposing 100 structured tools (81 core and 19 MCP App bridge tools) across 28 categories — CRUD, OData & FetchXML queries, metadata, batch, RBAC, solutions, audit, and schema write.
- Implemented three enterprise authentication modes (device code, client credentials, managed identity via MSAL) with AES-256-GCM encrypted token caching and guardrails on destructive operations.
- Distributed via npm/npx (mcp-dataverse, 8,000+ downloads) and published on the official MCP Registry; works with Claude, VS Code Copilot, Cursor, Windsurf, and any MCP client.
- Production-quality engineering: modular architecture, structured outputs, stdio + HTTP/SSE transports, automated tests, CI, documentation site, changelog, and public roadmap.
Agent Context & Memory Infrastructure
Creator · Lead
Internal context and memory system for AI-assisted development across large, multi-team codebases. Persists repository knowledge — architecture decisions, patterns, and team conventions — so coding agents retrieve the right context across sessions and team members.
- Team-level shared context and memory harness: reduces onboarding friction, context loss, and AI hallucination risk on unfamiliar codebases.
- Retrieval via vector search and Azure-native services across large, multi-team projects.
- Deployed and adopted across delivery teams for day-to-day AI-assisted development.
Agentic Delivery Framework
Creator · Lead
Installable, Copilot-native delivery framework that structures the full software delivery lifecycle — discovery, architecture, implementation, review, and production deployment — for AI-assisted teams.
- Enforces explicit human-in-the-loop checkpoints at architecture decisions, implementation gates, and ALM promotion — production governance for agentic delivery at scale.
- Runtime integrates MCP servers to ground recommendations on live project context; installable into any target project via CLI.
- Adopted across teams and business domains to scale structured agentic workflows.
