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/claude-skillsnpx skills add microsoft/DataFactory.MCP --skill claude-skillsgit 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/claude-skills)<a href="https://agentmods.dev/skills/microsoft/datafactory.mcp/claude-skills"><img src="https://agentmods.dev/badge/skills/microsoft/datafactory.mcp/claude-skills.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 | $0.00049 | $0.00968 |
| Opus 5 | $0.00024 | $0.00484 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
datafactory-tips 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Factory Tips
Operational knowledge for working with Microsoft Fabric Data Factory.
Must / Prefer / Avoid
MUST DO
- Use
executeOption = "ApplyChangesIfNeeded"on first refresh of API-created dataflows - Re-add connections via
add_connection_to_dataflowaftersave_dataflow_definition(save may wipe them) - Use
list_workspacesand filter by name — there is nofind_workspacetool - Validate each connection with
execute_queryafter adding - Create a new dataflow instead of reverting a multi-source one to single-source — there is no
remove_connectiontool
PREFER
- Filter early in M queries to enable query folding (push filters to source)
- Expensive operations (sorting, aggregation) last — streaming operations (filter, select) first
execute_querywithcustomMashupDocumentto iterate on M code before saving- Standard engine for complex transforms; Fast Copy only for simple ingestion
AVOID
get_authoring_guidance— deprecated, author M directly- Sorting early in query chains (requires reading all data before returning results)
SELECT *equivalent without row limits during development — use "Keep First Rows" then remove
Symptom Triage
| Symptom | Likely Cause | Read |
|---|---|---|
DataflowNeverPublishedError |
Default SkipApplyChanges on first run | destinations/dest-new-table.md |
DestinationColumnNotFound |
Manual mappings for new table | destinations/dest-new-table.md |
| Credentials error on Lakehouse | Connection not bound | datafactory-connections.md (Binding) |
| FastCopy fails with transforms | Unsupported transform in fast copy | datafactory-advanced.md (Fast Copy) |
| Instant refresh fail (0-3s) | Privacy firewall or unpublished draft | sources/multi-source.md |
| Multi-source instant fail via API | Dirty dataflow or separate Lakehouse.Contents calls | sources/multi-source.md |
IsNewTarget = false fails |
Direct navigation on API-created dataflow | destinations/dest-new-table.md |
| Stale connections after revert | save_dataflow_definition doesn't remove connections | datafactory-connections.md (Troubleshooting) |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- datafactory-advanced.md 4.2 KB
- datafactory-connections.md 9.6 KB
- datafactory-core.md 3.0 KB
- datafactory-performance.md 2.5 KB
- datafactory-pipelines.md 6.5 KB
- destinations/dest-existing-table.md 2.3 KB
- destinations/dest-new-table.md 4.3 KB
- destinations/dest-troubleshooting.md 3.6 KB
- sources/multi-source.md 2.6 KB
- sources/sharepoint-excel.md 1.7 KB
- templates/m-existing-table-destination.m 1.2 KB
- templates/m-multi-source-section.m 2.0 KB
- templates/m-new-table-destination.m 1.1 KB
- templates/m-sharepoint-excel-source.m 695 B
- templates/pipeline-chained-dataflows.json 1.7 KB
- templates/pipeline-single-dataflow.json 731 B
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.
- 5d ago First seen · 78 lines · 49 tokens per session scan A ef22b58d9774
datafactory-tips is a skill published in the GitHub repository microsoft/DataFactory.MCP (42 stars, last pushed 23d ago), licensed MIT. It adds 49 tokens to every session and 968 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…