Microsoft Fabric MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_CLIENT_ID | Yes | Your Azure client ID | |
| AZURE_TENANT_ID | Yes | Your Azure tenant ID | |
| AZURE_CLIENT_SECRET | Yes | Your Azure client secret | |
| POWERBI_WORKSPACE_ID | No | Power BI workspace ID. If not set, uses workspace-agnostic endpoints |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_powerbi_datasetsB | Get all Power BI datasets in the workspace |
| execute_dax_queryC | Execute a DAX query on a Power BI dataset |
| refresh_datasetC | Refresh a Power BI dataset |
| get_workspacesB | Get all Fabric/Power BI workspaces |
| create_notebookC | Create a new notebook in Fabric workspace |
| upload_to_datawarehouseC | Upload data to a Fabric Data Warehouse |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose targeting different resources and actions in the Microsoft Fabric ecosystem. For example, create_notebook handles notebook creation, execute_dax_query runs queries, get_powerbi_datasets retrieves datasets, get_workspaces lists workspaces, refresh_dataset updates datasets, and upload_to_datawarehouse uploads data, with no overlap or ambiguity between them.
The tool names follow a mostly consistent verb_noun pattern, such as create_notebook, execute_dax_query, and refresh_dataset. However, there is a minor deviation with get_powerbi_datasets and get_workspaces using 'get' instead of 'list', which is slightly inconsistent but still readable and predictable.
With 6 tools, the server is well-scoped for its purpose of managing Microsoft Fabric resources. Each tool earns its place by covering essential operations like data querying, workspace management, dataset handling, and data uploads, without being overly sparse or bloated.
The tool surface provides good coverage for core workflows in Microsoft Fabric, including workspace listing, dataset retrieval and refresh, query execution, notebook creation, and data upload. A minor gap exists in operations like updating or deleting resources, but agents can likely work around this for most tasks.