Intellify Remote Power BI 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., "@Intellify Remote Power BI MCP Servershow me the tables in the Sales semantic model"
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.
Intellify Remote Power BI MCP Server
Production-oriented remote semantic-model engineering for Microsoft Fabric and Power BI. The target system lets authorized AI agents inspect, query, create, modify, validate, refresh, and manage eligible cloud semantic models through stateless Streamable HTTP.
The repository is being delivered phase by phase according to implementation.md. Phases 0–6 establish the engineering foundation, secure remote boundary, provider and definition engines, reads, transactional and advanced authoring, lifecycle operations, agent-safe planning, resilience, and recovery. Phase 7 adds enterprise security, privacy, distributed observability, append-only audit, alerting, and service management. Hosted Render and live tenant certification remain explicit Phase 8 release gates.
Current status
Secure MCP 2026-07-28 Streamable HTTP control plane on Node.js 24 LTS.
Tenant-specific Entra token validation, downstream OBO/workload token providers, encrypted partitioned cache, and authorization policy.
Internal .NET 10 XMLA adapter trust contract with workload JWT authentication and short-lived execution-grant validation.
Fixed-origin, retry-budgeted Fabric and Power BI REST clients with explicit long-running-operation handles and typed provider errors.
Unknown-preserving TMSL definition engine with bounded decoding, immutable transformations, canonical indexes, versioned fingerprints, semantic diffing, and golden fixtures.
Five policy-filtered MCP read tools for discovery, capability resolution, inspection, definition retrieval, DAX/INFO queries, and durable operation status.
Three policy-filtered authoring tools for immutable planning, validation/approval, and apply, covering core model, table, column, measure, and relationship lifecycle changes.
Advanced typed authoring for hierarchies, calculation groups/items, partitions, roles and table permissions, perspectives, named expressions, cultures, translations, and extended table/column/relationship metadata.
Transactional-by-default model/table/partition refresh, Fabric model lifecycle, exact-target hard deletion, ownership-checked connection binding, and bounded administrative diagnostics.
Per-model leases, idempotency, stale-base checks, ETag operation transitions, encrypted prechange snapshots, semantic verification, reconciliation, and compensation.
Internal TOM transactional read/write, TMDL conversion, ADOMD.NET DAX/MDX/DMV/schema readers, restricted traces, and an authenticated versioned TypeScript client.
Typed Arrow and JSON normalization with LZ4 support, deterministic row/byte/time limits, private expiring artifacts, and horizontally durable read-operation state.
Strict domain, application, and contract boundaries.
JSON/SSE, query cancellation/truncation, two-replica state, malformed-input, authorization, redaction, and official MCP Inspector tests.
Credential-gated Fabric, Power BI, XMLA, OBO, and delegated-RLS integration harnesses.
Active W3C traces, Azure Monitor OpenTelemetry, safe service metrics, HMAC-pseudonymized append-only audit, dashboards, alerts, SLOs, and operational runbooks.
Private Azure networking, hardened Storage, Key Vault, managed identity, Container Apps, Container Registry, and monitoring IaC.
Pull-request CI, CodeQL, dependency and Trivy scanning, image SBOMs, and release-metadata automation.
See docs/evidence/phase-7/validation-status.md for the current gate status, docs/api/semantic-model-write-tools.md for the authoring contract, and docs/api/semantic-model-operations.md for operational actions. Credential-gated cloud and deployment tests are pending evidence, not passes.
Related MCP server: Microsoft Fabric MCP Server
Prerequisites
Node.js
24.14.0pnpm
11.25.0through Corepack.NET SDK
10.0.400or DockerDocker for final Linux-image validation
Azure CLI with Bicep for infrastructure compilation
Local validation
corepack pnpm install --frozen-lockfile
corepack pnpm ci:typescript
dotnet restore PowerBi.RemoteMcp.slnx
dotnet build PowerBi.RemoteMcp.slnx --configuration Release --no-restore
dotnet run --project apps/xmla-adapter/tests/PowerBi.XmlaAdapter.UnitTests --configuration Release --no-build
dotnet run --project apps/xmla-adapter/tests/PowerBi.XmlaAdapter.IntegrationTests --configuration Release --no-buildIf .NET 10 is not installed locally, run the .NET checks through the pinned SDK container as described in docs/architecture/development-workflow.md.
Local application
Build and start the TypeScript control plane:
corepack pnpm build
corepack pnpm start:mcpTypeScript health:
GET http://localhost:3000/health/liveTypeScript readiness:
GET http://localhost:3000/health/readyOAuth resource metadata:
GET http://localhost:3000/.well-known/oauth-protected-resourceSecure MCP:
POST http://localhost:3000/mcp.NET container health:
GET http://localhost:8080/health/live
The default development process generates an unlogged random MCP token and therefore denies callers unless MCP_DEVELOPMENT_TOKEN is explicitly set. Development authentication cannot start outside the development environment. See docs/api/mcp-client-configuration.md and docs/security/entra-application-registration.md.
Semantic-model writes are also disabled by default. Do not enable WRITE_MODEL_ENABLED until the private adapter audience, execution-grant key pair, 32-byte approval/snapshot and audit-hashing keys, durable append-only audit, durable state storage, workload identity, and target/risk authorization policy are configured. See docs/architecture/semantic-write-safety.md and the live XMLA gate.
Security
Do not place credentials, access tokens, connection strings, model definitions, or query results in source control or issues. Read SECURITY.md, the threat model, and the privacy and LLM data-handling guidance before adding an integration.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
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.
Related MCP Connectors
- mcp-serverOAuthcom.make
Give your AI agents the tools to build, manage, and run automation workflows.
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Debug, build, and manage Power Automate cloud flows with AI agents
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to programmatically manage Power BI workspaces, reports, and dashboards while executing DAX queries and triggering dataset refreshes. It supports secure OAuth2 authentication for operations like report exporting, workspace management, and real-time push dataset updates.624MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with Microsoft Fabric and Power BI services through the Model Context Protocol. Users can manage workspaces, execute DAX queries, refresh datasets, and create Fabric notebooks using natural language.6222MIT
- AlicenseBqualityAmaintenanceEnables AI agents to interact with Microsoft Fabric Real-Time Intelligence services, allowing for seamless data querying, analysis, and streaming capabilities.39130MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI applications to interact with Power BI through the Model Context Protocol, supporting comprehensive API operations including data retrieval and management.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/Kkb113/Intellify_Remote_PowerBI_MCP_Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server