Fabric RTI MCP Server is a Model Context Protocol server that gives AI agents tools for querying and managing Microsoft Fabric Real-Time Intelligence services, including Eventhouse, Azure Data Explorer, Eventstreams, and Activator. It is for agents and users who need natural-language access to real-time analytics and streaming workflows through KQL and service-management operations. The catalogue add-ons provide instructions and skills for using the server.
Borrowing it
Nothing to install: this file belongs to microsoft/fabric-rti-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/fabric-rti-mcp/main/.github/skills/kql/SKILL.mdgit clone --depth 1 https://github.com/microsoft/fabric-rti-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/fabric-rti-mcp/kql)<a href="https://agentmods.dev/skills/microsoft/fabric-rti-mcp/kql"><img src="https://agentmods.dev/badge/skills/microsoft/fabric-rti-mcp/kql.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00159 | $0.06444 |
| Opus 5 | $0.00079 | $0.03222 |
| Sonnet 5 | $0.00032 | $0.01289 |
| Haiku 4.5 | $0.00016 | $0.00644 |
Grade A, and why
kql 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 8d 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 — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KQL Mastery
Try it yourself: All
✅examples in this skill can be run against the public help cluster:https://help.kusto.windows.net, databaseSamples(containsStormEvents,SimpleGraph_Nodes/Edges,nyc_taxi, and more).
1. Running KQL with Fabric RTI MCP
Fabric RTI MCP exposes Kusto functionality as MCP tools. Authentication is handled transparently using Azure Identity.
Available tools
| Tool | Purpose |
|---|---|
kusto_query |
Execute a KQL query on a database |
kusto_command |
Execute a management command (.show, .create, etc.) |
kusto_list_entities |
List databases, tables, external tables, materialized views, functions, graphs |
kusto_describe_database |
Get schema for all entities in a database |
kusto_describe_database_entity |
Get schema for a specific entity (table, function, etc.) |
kusto_sample_entity |
Get sample data from a table or other entity |
kusto_graph_query |
Execute a graph query using snapshots or transient graphs |
kusto_ingest_inline_into_table |
Ingest inline CSV data into a table |
kusto_known_services |
List configured Kusto services |
kusto_get_shots |
Retrieve semantically similar shots from a shots table |
kusto_deeplink_from_query |
Build a deeplink URL to open a query in the web explorer |
kusto_show_queryplan |
Get the execution plan for a query without running it |
kusto_diagnostics |
Get a best-effort cluster health and capacity summary |
Query vs management commands
KQL has two execution planes, each with its own MCP tool:
| Plane | Tool | Starts with | Examples |
|---|---|---|---|
| Query | kusto_query |
Table name, let, print, datatable |
StormEvents | where State == "TEXAS" |
| Management | kusto_command |
.show, .create, .set, .drop, .alter |
.show tables, .show table T schema |
Basic usage
# Query plane — use kusto_query
kusto_query(
cluster_uri="https://help.kusto.windows.net",
database="Samples",
query="StormEvents | summarize count() by EventType | top 5 by count_ desc"
)
# Management plane — use kusto_command
kusto_command(
cluster_uri="https://help.kusto.windows.net",
database="Samples",
command=".show tables"
)
# Schema exploration — use kusto_describe_database or kusto_describe_database_entity
kusto_describe_database(
cluster_uri="https://help.kusto.windows.net",
database="Samples"
)
# Sample data — use kusto_sample_entity
kusto_sample_entity(
cluster_uri="https://help.kusto.windows.net",
database="Samples",
entity_name="StormEvents",
entity_type="table",
sample_size=5
)
# Graph queries — use kusto_graph_query
kusto_graph_query(
cluster_uri="https://mycluster.kusto.windows.net",
database="MyDB",
graph_name="MyGraph",
query="| graph-match (node) project labels=labels(node)"
)
# Deeplinks — use kusto_deeplink_from_query
kusto_deeplink_from_query(
cluster_uri="https://help.kusto.windows.net",
database="Samples",
query="StormEvents | count"
)
What ships with it
4 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.
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.
- 8d ago First seen · 580 lines · 159 tokens per session scan A bc34dd6cdf52
kql is a skill published in the GitHub repository microsoft/fabric-rti-mcp (130 stars, last pushed 6d ago), licensed MIT. It adds 159 tokens to every session and 6,444 once invoked, about $0.0008 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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…