Microsoft Data Factory MCP Server is an MCP server for discovering and managing Microsoft Fabric resources through a standardized interface. Agents and developers use it to work with gateways, connections, workspaces, dataflows, pipelines, copy jobs, Airflow jobs, and capacities.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/datafactory.mcp/architecture.mcp-toolsnpx skills add microsoft/DataFactory.MCP --skill architecture.mcp-toolsgit clone --depth 1 https://github.com/microsoft/DataFactory.MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/datafactory.mcp/architecture.mcp-tools)<a href="https://agentmods.dev/skills/microsoft/datafactory.mcp/architecture.mcp-tools"><img src="https://agentmods.dev/badge/skills/microsoft/datafactory.mcp/architecture.mcp-tools.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.00703 |
| Opus 5 | $0.00016 | $0.00351 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
architecture.mcp-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding MCP Tools — Patterns
For the full architecture, see docs/ARCHITECTURE.md.
Overview
Every new MCP capability follows the Tool → Service → Model pattern:
1. Define Models (DataFactory.MCP.Core/Models/)
2. Define Interface (DataFactory.MCP.Core/Abstractions/)
3. Implement Service (DataFactory.MCP.Core/Services/)
4. Implement Tool (DataFactory.MCP.Core/Tools/)
5. Register in DI (DataFactory.MCP.Core/Extensions/)
6. Add Tests (DataFactory.MCP.Tests/)
Step-by-Step
1. Models — Define data shapes
Create request/response DTOs in Models/. Keep them as pure data containers — no business logic.
2. Interface — Define the service contract
Add to Abstractions/. The interface defines what operations are available.
3. Service — Implement Fabric API calls
Create in Services/. Follow existing services as examples:
FabricGatewayService.cs— Gateway CRUD operationsFabricConnectionService.cs— Connection managementFabricDataflowService.cs— Dataflow operations
Key patterns:
- Inject
HttpClient(configured with auth handler) - Use
AuthenticationServicefor token management - Return strongly-typed models
- Handle HTTP errors gracefully
4. Tool — Implement MCP interface
Create in Tools/. Follow existing tools as examples:
GatewayTool.cs— Simple CRUD toolsConnectionsTool.cs— Tools with UI resourcesDataflow/— Complex multi-tool directory
Key patterns:
- Define tool name, description, and JSON schema for parameters
- Validate inputs before calling service
- Format responses for MCP protocol
- Handle auth-not-ready state
5. DI Registration
Register new services and tools in Extensions/ so they're available at runtime.
6. Tests
Add xUnit tests in DataFactory.MCP.Tests/:
- Test parameter validation
- Test service response parsing
- Test error handling paths
Existing Tools Reference
| Tool File | Service | Capability |
|---|---|---|
AuthenticationTool.cs |
AuthenticationService |
Azure AD auth flows |
GatewayTool.cs |
FabricGatewayService |
Gateway CRUD |
ConnectionsTool.cs |
FabricConnectionService |
Connection management |
WorkspacesTool.cs |
FabricWorkspaceService |
Workspace listing |
CapacityTool.cs |
FabricCapacityService |
Capacity management |
Dataflow/ |
FabricDataflowService |
Dataflow operations |
Pipeline/ |
FabricPipelineService |
Pipeline management |
CopyJob/ |
FabricCopyJobService |
Copy job management |
CreateConnectionUITool.cs |
FabricConnectionService |
UI wizard for connections |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 87 lines · 33 tokens per session scan A f6950cdebe95
architecture.mcp-tools is a skill published in the GitHub repository microsoft/DataFactory.MCP (42 stars, last pushed 23d ago), licensed MIT. It adds 33 tokens to every session and 703 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…