The d365fo-client + MCP Server.
Production-ready Model Context Protocol server for Microsoft Dynamics 365 Finance & Operations. Connect AI assistants — GitHub Copilot, Claude Desktop, VS Code — with one-click installation and 34 specialized tools.
From hours of config to one click.
The full configuration was manual JSON, environment variables, and dependency hell.
It's now a single button that prompts for credentials and installs the server with uvx dependency management.
34 tools across 7 functional categories.
Production-ready coverage of every major D365 F&O operation surface — connection, CRUD, metadata, labels, profiles, sync, performance.
Connectivity testing & environment info.
Advanced OData querying & entity management.
Entity search, schema analysis, enumeration discovery.
Multi-language label operations & batch processing.
Multi-environment configuration & credential management.
Sync session orchestration with progress reporting.
Caching, FTS5 search, query plan inspection.
Drop into any MCP-compatible client.
Native MCP support for code workflows.
Direct config with uvx dependency management.
Built-in MCP integration; one-click install.
Standard MCP protocol for any compatible client.
Three ways to install.
# one-click install
Click the button above
# auto-prompts for credentials
No manual config required.Automatic dependency management with uvx.
# add to Claude config
"command": "uvx",
"args": ["--from", "d365fo-client",
"d365fo-mcp-server"]Always pulls the latest released version.
# install from PyPI
pip install d365fo-client
# start the MCP server
d365fo-mcp-serverTraditional install for custom setups.
Posts about d365fo-client + MCP.
Implementation notes, deeper dives, and release breakdowns.
RAG Evaluation in Production: Moving Beyond Metrics for Enterprise Success
Your enterprise RAG app works in the lab, but how does it perform in production? Discover advanced strategies beyond static metrics to ensure reliability and business value.
From Wall Street to ERP: Why Transformer Embeddings Are Eating Enterprise Transaction Systems
Enterprise ERP logs are high-signal event streams. By applying sequence-based transformers (like Revolut’s PRAGMA) and Tabular Foundation Models (like Prior Labs’ TabPFN) to ERP data, we can build unified, multi-task systems that outperform custom feature engineering.
The ERP Copilot Security Dilemma: Dynamic Row-Level Security and Identity Delegation in LLMs
Naive Service Principal access exposes sensitive ERP data to LLM context windows. Learn how to architect zero-trust AI agents using OAuth2 On-Behalf-Of (OBO) token exchange and database-enforced Row-Level Security (RLS).
Beyond the Prompt: Context Engineering Patterns for Complex Enterprise APIs
Enterprise APIs are too massive for LLM prompts. Discover context engineering patterns like JIT schema pruning, semantic routing, and session compression to build efficient agents.
Microsoft Agent Framework 1.0 for .NET: The Agentic Runtime .NET Developers Have Been Waiting For
Microsoft Agent Framework 1.0 unifies AutoGen and Semantic Kernel into a single, production-ready agentic runtime for .NET. A deep-dive for product owners, architects, and developers — with a real expense-tracker agent built in C# to show how it all fits together.
D365 F&O Client & MCP Server v0.3.7: Request Tracing & Server Timing Are Here
D365 F&O Client & MCP Server v0.3.7 ships comprehensive request tracing and server timing visibility — making production debugging and performance analysis dramatically easier.
Have a hard AI problem?
I work with a small number of teams each quarter — usually on production LLM pipelines, MCP integrations with enterprise systems, or evaluation frameworks that survive contact with real data.