Force FabricSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Force Fabric MCP Server
Detect issues. Auto-fix problems. Optimize your Fabric tenant. An MCP server that scans Lakehouses, Warehouses, Eventhouses, Semantic Models, and Gateways with 158+ diagnostic rules — and can auto-fix 67 of them.
Quick Start • Detect • Auto-Fix • Rules • Architecture
Key Features
Detect — 158+ Rules Across 5 Fabric Item Types
Fix — 67 Auto-Fixable Issues
Unified Output
Every scan returns a clean results table — only issues shown, passed rules counted in summary:
29 rules — 18
c6d2dfa543e7OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add fabric-optimization-mcp-server --env AZURE_CLIENT_SECRET=${AZURE_CLIENT_SECRET} -- npx -y [email protected]{
"mcpServers": {
"fabric-optimization-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AZURE_CLIENT_SECRET": "${AZURE_CLIENT_SECRET}"
}
}
}
}Exposed tools (33)
31 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
auth_login | read | Login to Microsoft Fabric. MUST be called before using any other tool. |
auth_logout | destructive | Logout from Microsoft Fabric and clear cached credentials. |
auth_status | read | Check if you are currently authenticated to Microsoft Fabric. |
eventhouse_auto_optimize | read | AUTO-OPTIMIZE: Scans a Fabric Eventhouse for all fixable issues across all KQL databases and applies fixes. |
eventhouse_fix | read | AUTO-FIX: Applies fixes to a Fabric Eventhouse. |
eventhouse_fix_materialized_views | read | AUTO-FIX: Diagnoses and repairs broken materialized views in a Fabric Eventhouse. |
eventhouse_list | read | List all eventhouses in a Fabric workspace with their query/ingestion URIs and KQL database counts. |
eventhouse_list_kql_databases | read | List all KQL databases in a Fabric workspace. |
eventhouse_optimization_recommendations | read | LIVE SCAN: Connects to a Fabric Eventhouse KQL endpoint and runs real diagnostic commands. |
fabric_optimization_report | read | Generate a comprehensive optimization report for an entire Fabric workspace. |
gateway_fix | read | AUTO-FIX: Applies fixes to gateway and connection issues. |
gateway_list | read | List all gateways with their status, version, type, and VNet configuration. |
gateway_list_connections | read | List all connections with their connectivity type, gateway binding, and privacy level. |
gateway_optimization_recommendations | read | LIVE SCAN: Scans all gateways and connections with 12 rules covering availability (online status, connectivity), |
lakehouse_auto_optimize | read | AUTO-OPTIMIZE: Discovers ALL Delta tables in a Lakehouse and applies fixes to every table |
lakehouse_fix | read | AUTO-FIX: Applies Spark SQL fixes to a Lakehouse via Livy API (no notebooks needed). |
lakehouse_get_job_status | read | Check the status of a table maintenance job on a Fabric Lakehouse. |
lakehouse_list | read | List all lakehouses in a Fabric workspace with their metadata, SQL endpoint status, and OneLake paths. |
lakehouse_list_tables | read | List all tables in a Fabric Lakehouse with their type, format (Delta/Parquet), and location. |
lakehouse_optimization_recommendations | read | LIVE SCAN: Analyzes a Fabric Lakehouse by checking table formats (Delta vs non-Delta), |
lakehouse_run_table_maintenance | write | Run table maintenance (OPTIMIZE with V-Order, Z-ORDER, VACUUM) on a Fabric Lakehouse. |
semantic_model_auto_optimize | read | AUTO-OPTIMIZE: Applies all 19 safe fixes to a Semantic Model using XMLA/TMSL commands |
semantic_model_fix | read | AUTO-FIX: Uses XMLA/TMSL commands for atomic per-object fixes (measures, columns, tables). |
semantic_model_list | read | List all semantic models in a Fabric workspace. |
semantic_model_optimization_recommendations | read | LIVE SCAN: Connects to a Fabric Semantic Model and executes DAX queries (COLUMNSTATISTICS) |
warehouse_analyze_query_patterns | read | LIVE SCAN: Connects to a Fabric Warehouse SQL endpoint and analyzes real query execution |
warehouse_auto_optimize | read | AUTO-OPTIMIZE: Scans a Fabric Warehouse for all fixable issues and applies all safe fixes automatically. |
warehouse_fix | read | AUTO-FIX: Connects to a Fabric Warehouse and applies fixes for detected issues. |
warehouse_list | read | List all warehouses in a Fabric workspace with their metadata and connection details. |
warehouse_optimization_recommendations | read | LIVE SCAN: Connects to a Fabric Warehouse SQL endpoint and runs real diagnostic queries. |
workspace_capacity_info | read | List Fabric capacities with their SKU, state, and region. Includes capacity optimization tips. |
workspace_list | read | List all Fabric workspaces you have access to with their IDs, types, and capacity assignments. |
workspace_list_items | read | List all items in a Fabric workspace, optionally filtered by type (Lakehouse, Warehouse, |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
auth_logout
@azure/identity, @modelcontextprotocol/sdk, fast-xml-parser, tedious, @types/node, typescript
banner.png
Gates applied: no_behavioural_pass.
c6d2dfa543e7full audit observations/trust-audit/mcp-server/tmdaidevs__force-fabric.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | c6d2dfa543e7 | SAFE | B | 89 | first audit |
Questions
What tools does Force Fabric expose?
33 in total: 31 read-only, 1 that write, and 1 that can delete or overwrite (auth_logout). Every one is listed on this page with its risk.
Is Force Fabric safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Force Fabric need?
It reads AZURE_CLIENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Force Fabric run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as fabric-optimization-mcp-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (c6d2dfa543e7), read on 2026-10-09. The repository is watched and re-audited when it changes.