Fabric-Analytics-MCP

An MCP (Model Context Protocol) server that exposes a large set of tools for authenticating to Microsoft Fabric and performing analytics/workspace operations, including CRUD for Fabric items, Spark/Livy job and monitoring workflows, and Synapse-to-Fabric migration tooling. It also supports local/Docker/Kubernetes-style deployment patterns and multiple Fabric authentication approaches.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp microsoft-fabric analytics spark livy synapse-to-fabric workspace-management observability kubernetes docker authentication
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
61
/ 100
Is it safe for agents?
⚡ Reliability
38
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
55
Error Messages
0
Auth Simplicity
70
Rate Limits
20

🔒 Security

TLS Enforcement
80
Auth Strength
70
Scope Granularity
35
Dep. Hygiene
55
Secret Handling
60

Security is largely delegated to Microsoft Fabric auth and the server's own token handling. README highlights bearer token usage and token refresh/validation and mentions a simulation mode and a 10-second timeout protection, which may reduce hangs. However, the provided materials do not clearly document audit logging redaction, secure storage of secrets, least-privilege scope granularity, rate limiting, or how tool outputs handle sensitive data.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
50
Error Recovery
45
AF Security Reliability

Best When

You run a self-hosted MCP server inside your environment and want LLM agents to orchestrate Microsoft Fabric administration and migration workflows via authenticated tool calls.

Avoid When

You cannot securely manage bearer tokens/client secrets, or you need strong guarantees about operational safeguards (rate limits, structured error codes, idempotency for create/delete/update) that are not clearly documented.

Use Cases

  • Let an AI agent inspect and manage Microsoft Fabric workspaces and items (notebooks, lakehouses, datasets, reports, etc.)
  • Automate Spark job submission/monitoring via Fabric/Livy-style workflows through MCP tools
  • Perform or assist with Synapse-to-Fabric notebook/workload migration using discovery, transformation, and provisioning/dry-run steps
  • Provision and manage Fabric environments, capacities, and permissions programmatically via an MCP-compatible interface
  • Run end-to-end tests that create real Fabric resources and validate job execution

Not For

  • Direct public, unauthenticated access to Fabric/enterprise resources
  • Highly regulated environments where token handling, logging, and audit guarantees must be independently verified from source/runtime evidence
  • Use cases requiring a hosted SaaS with documented SLAs (this appears to be a self-hosted MCP server)
  • Scenarios where idempotent/destructive operations cannot be carefully controlled

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Bearer token (FABRIC_AUTH_METHOD=bearer_token, FABRIC_TOKEN) Azure CLI authentication (uses az login session) Service Principal Device Code Interactive Simulation mode (bearerToken: "simulation")
OAuth: No Scopes: No

README describes multiple auth methods and includes a recommendation to prefer bearer tokens to avoid interactive auth timeouts in sandboxed environments. Specific scope granularity for Fabric permissions is not evidenced in the provided text.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; appears to be open-source/self-hosted.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Interactive authentication flows can time out in sandboxed MCP clients; bearer-token flow is recommended.
  • Tokens expire (~1 hour per README), so long-running sessions may require refresh logic or re-auth.
  • Destructive operations (e.g., deletes, unassigning/migration) may require additional confirmation/guardrails from the agent/operator.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Fabric-Analytics-MCP.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered