Search for a command to run...
Use workspace monitoring to monitor MCP server use
Principal Program Manager, Microsoft Fabric CAT helping users and organizations build scalable, insightful, secure solutions. Blogs, opinions are my own and do not represent my employer.
No comments yet. Be the first to comment.
Last week Microsoft released an open-source text embedding model called Harrier in three sizes- 270M, 0.6B and 27B. I have been testing it in my RAG pipeline and so far it has crushed all my metrics.
For Power BI Copilot and Data agents with semantic models, you must use Prep Data for AI configuration to ground the responses in the context added in Prep for AI. In this blog, I will show you how yo
At FabCon Atlanta last week, the updated notebook Copilot for data engineering and data science was announced. It brings agentic capabilities to the Copilot and is much more intelligent and Fabric-awa
Using Fabric data agent Python SDK
Power BI Modeling MCP server was launched at Ignite 2025 last month. It has quickly become an indispensable tool for working with the semantic models in Fabric workspaces. You can learn more about it below:
Announcement by Rui Romano : https://powerbi.microsoft.com/en-us/blog/power-bi-november-2025-feature-summary/#post-31766-_Toc214035083
Documentation : Power BI MCP server documentation - Power BI | Microsoft Learn
Blog by Jeffrey Wang : Talk to Your Data Model: Introducing the Power BI Modeling MCP – pbidax
I was recently asked how admins can monitor usage of the Modeling MCP Server. Similar to any other external tool, if a user has permission to query a semantic model’s XMLA endpoint, you cannot restrict which client or tool they use. However, admins can monitor its usage.
Enable Workspace Monitoring : Turn on Workspace Monitoring, you will need to be a Workspace Admin to enable this. I have a blog on how this can be helpful.
Query the logs : Query the SemanticModelLogs table and identify the semantic models that are being queried and which users. Filter the ApplicationName column to find the application used for querying the model.
// Monitor Power BI Modeling Server Usage
SemanticModelLogs
| where ItemKind == 'Dataset' and ApplicationName == 'MCP-PBIModeling'
| summarize sessions = dcount(OperationId) by ItemName, ExecutingUser, ApplicationName, bin(Timestamp, 5m)
