fabric-mcp-server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fabric-mcp-serverList recent pipeline runs in Sales workspace"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fabric-mcp-server
A Model Context Protocol server for Microsoft Fabric. It gives an MCP client (Claude Code, Claude Desktop, etc.) read access to Fabric data-pipeline run history and read-only DAX queries against semantic models — plus optional job control behind a write flag.
It talks to the public Fabric REST API (api.fabric.microsoft.com) and the Power BI REST API (api.powerbi.com), authenticating with @azure/identity so you can run it interactively, headless (device code), via the Azure CLI, or as a service principal.
Features
Resolve workspaces, pipelines, and semantic models by display name or GUID — no need to hunt for IDs.
Continuation-token paging and HTTP 429 retry (honors
Retry-After) built in.Read-only by default; pipeline execution is gated behind an explicit write mode.
Related MCP server: MCP Server for Power BI
Tools
Tool | Mode | Description |
| read | List all Fabric workspaces the signed-in identity can see. |
| read | List items in a workspace (notebooks, lakehouses, warehouses, semantic models, reports, pipelines), optional type filter. |
| read | List the data pipelines in a workspace. |
| read | Run (job instance) history for a pipeline, most-recent first, optional status filter. |
| read | Full detail for one run by job instance ID, including |
| read | Recent refresh history for a semantic model, most-recent first — did the refresh succeed, and why did it fail. |
| read | Items changed between the workspace and its connected Git branch, plus remote commit hash and workspace head. |
| read | Get an item's definition parts (semantic model TMDL, notebook content, report). Manifest by default; decoded contents for a named part. |
| read | Run a read-only DAX query against a semantic model (Power BI |
| write | Trigger an on-demand pipeline run. |
| write | Cancel an in-progress run. |
| write | Trigger an on-demand refresh of a semantic model. |
| write | Update a workspace from its connected Git branch (pull repo → workspace), preferring remote on conflicts. |
| write | Deploy an item definition from a local folder, overwriting the live item. Snapshots the current definition first for one-call rollback. |
The write tools are only registered when FABRIC_MCP_MODE=write.
Requirements
Node.js >= 20
An Entra (Azure AD) identity with access to the target Fabric workspace(s).
For
execute_dax: Build permission on the target semantic model, and the tenant's "Dataset Execute Queries REST API" admin setting enabled.
Install
git clone <this-repo-url> fabric-mcp-server
cd fabric-mcp-server
npm installConfiguration
All configuration is via environment variables (see .env.example). Set them in your MCP client's env block, or copy .env.example to .env for local debugging.
Variable | Required | Purpose |
| no (default |
|
| for interactive / device-code / service-principal | Your Entra tenant ID. |
| for service-principal | App registration client ID. |
| for service-principal | App registration secret. |
| no (default |
|
Auth modes
interactive — opens a browser; best for desktop/AVD.
device-code — prints a code + URL to stderr; for SSH / WSL / headless.
cli — reuses your existing
az loginsession.service-principal — non-interactive with client ID + secret.
managed-identity — for hosting on Azure.
default — tries env → managed-identity → CLI → browser in turn.
Use with Claude Code / Claude Desktop
Add to your MCP client config (e.g. ~/.claude.json for Claude Code, or claude_desktop_config.json):
{
"mcpServers": {
"fabric": {
"command": "node",
"args": ["/absolute/path/to/fabric-mcp-server/index.js"],
"env": {
"FABRIC_AUTH_MODE": "interactive",
"AZURE_TENANT_ID": "<your-entra-tenant-id>"
}
}
}
}To enable pipeline execution, add "FABRIC_MCP_MODE": "write" to the env block.
Examples
Check last night's run of a pipeline:
"Using fabric, how did my_pipeline run in My-Workspace last night?" →
list_pipeline_runs→get_pipeline_runon the failed instance.
Validate a measure against a live model:
"Run this DAX against the Production Analytics model in My-Workspace:
EVALUATE ROW("Sales", [Total Sales])" →execute_daxreturns the row.
Security notes
No secrets are stored in the repo. Credentials come from environment variables at runtime;
.envis git-ignored.The write tools (
run_pipeline,cancel_pipeline_run,refresh_dataset,update_from_git,update_item_definition) are only exposed underFABRIC_MCP_MODE=write, and each logs an[AUDIT]line to stderr.update_item_definitionoverwrites the live item wholesale; it snapshots the current definition to a local JSON first (under the OS temp dir) and returns the path so you can roll back withrestore_snapshot.execute_daxuses the Power BIexecuteQueriesAPI, which only runs read-only DAX (data-modifying queries are rejected by the service).
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/user-vik/fabric-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server