fabric-mcp-server (user-vik/fabric-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 62 out of 100, grade C. It declares 14 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
62/100

fabric-mcp-server

Enables read-only access to Microsoft Fabric data-pipeline run history and DAX queries against semantic models, with optional write mode for pipeline execution and dataset refresh.

→ user-vik/fabric-mcp-server· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

user-vik

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: AZURE_CLIENT_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes14 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_workspaces

List all Microsoft Fabric workspaces the signed-in identity can see.

list_pipelines

List the data pipelines in a Fabric workspace. Accepts a workspace display name (e.g. "My-Workspace") or GUID.

list_pipeline_runs

List run (job instance) history for a Fabric data pipeline, most-recent first. Accepts workspace + pipeline by display name or GUID. Use this for 'how did my pipeline run last night' style questions.

get_pipeline_run

Get full detail for a single pipeline run (job instance) by its ID, including failureReason. Use after list_pipeline_runs to drill into a failure.

execute_dax

Run a read-only DAX query against a Fabric/Power BI semantic model and return the result rows. Accepts workspace + dataset (semantic model) by display name or GUID. Use to validate measures or run ad-hoc analytics against a live model, e.g. 'EVALUATE ROW("x", [Some Measure])'. Read-only: the Power B…

list_items

List items in a Fabric workspace — notebooks, lakehouses, warehouses, semantic models, reports, data pipelines, etc. Optional type filter. Accepts workspace by display name or GUID.

get_refresh_history

Get recent refresh history for a semantic model (dataset), most-recent first — check whether a scheduled or on-demand refresh succeeded and why it failed. Accepts workspace + dataset by display name or GUID.

get_git_status

Show the Git status of a Fabric workspace: items changed between the workspace and its connected Git branch, plus the remote commit hash and workspace head. Requires the workspace to be connected to Git.

get_item_definition

Get the definition (source parts) of a Fabric item — semantic model TMDL, notebook content, report, etc. By default returns a manifest of part paths (no payloads, to stay small); pass 'part' with a path to get that file's decoded contents. Useful for inspecting or backing up a live item before deplo…

run_pipeline

Trigger an on-demand run of a Fabric data pipeline. Returns the accepted operation location. Requires FABRIC_MCP_MODE=write.

cancel_pipeline_run

Cancel an in-progress pipeline run (job instance). Requires FABRIC_MCP_MODE=write.

refresh_dataset

Trigger an on-demand refresh of a semantic model (dataset). Returns the accepted request; use get_refresh_history to track completion. Accepts workspace + dataset by display name or GUID. Requires FABRIC_MCP_MODE=write.

update_from_git

Update a Fabric workspace from its connected Git branch (pull repo -> workspace). Reads the current Git status to resolve the target commit, then updates, preferring the remote branch on conflicts. Long-running: poll get_git_status for completion. Requires the workspace to be connected to Git and FA…

update_item_definition

Deploy an item definition (semantic model, notebook, report, ...) to a live Fabric workspace from a local definition folder, OVERWRITING the item's current definition. Safety: snapshots the current live definition to a local JSON first (returned as snapshotPath) so you can roll back via restore_snap…

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.18.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.18.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.18.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configAZURE_CLIENT_IDfor service-principal App registration client ID.
🔐 secretAZURE_CLIENT_SECRETfor service-principal App registration secret.
configAZURE_TENANT_IDfor interactive / device-code / service-principal Your Entra tenant ID.
configFABRIC_AUTH_MODEno (default interactive) interactive, device-code, cli, service-principal, managed-identity, or default.
configFABRIC_MCP_MODEThe write tools are only registered when =write.
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

14/14 tools missing one or more hints — list_workspaces (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_pipelines (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_pipeline_runs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.18.0 (high), @modelcontextprotocol/sdk@1.18.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/user-vik/fabric-mcp-server?variant=verified)](https://m8ven.ai/mcp/user-vik/fabric-mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 355b034c7dd6f2d62c63d7dea4f48f2955b470b2
code hash: cd889df69f14cea9b5fb1f542b95d9d2f506b1e5fd6d31821031d9567dccc219
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client