azure-mcp-connection

azure-mcp-connection is a skill for Claude Code from WYRE-AI/msp-claude-plugins. It costs 68 tokens per session (1,426 once invoked), scanned A, original, Apache-2.0.

A setup guide for connecting an Azure account to the gateway through an Azure service principal, which is an application identity used for automated access. It covers read-only permissions and connection checks.

In plain words
What is it for?
Use it to register Azure credentials, assign Reader access, limit available Azure operations, and verify the connection.
Why use it?
It helps avoid connection failures caused by expired credentials, missing permissions, or incorrect tenant and client details.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Part of the azure-mcp plugin — 3 skills, 2 commands, 1 agent shipped together

Good fit Use it to register Azure credentials, assign Reader access, limit available Azure…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wyre-ai/msp-claude-plugins/connection
Install

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.

Any agent
npx skills add WYRE-AI/msp-claude-plugins --skill connection
Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install azure-mcp, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 1 agent.

Wrote 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.

agentmods badge for azure-mcp-connection

README.md
[![agentmods](https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/connection.svg)](https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/connection)
Your own site
<a href="https://agentmods.dev/skills/wyre-ai/msp-claude-plugins/connection"><img src="https://agentmods.dev/badge/skills/wyre-ai/msp-claude-plugins/connection.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,426 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01426
Opus 5 $0.00034 $0.00713
Sonnet 5 $0.00014 $0.00285
Haiku 4.5 $0.00007 $0.00143

Measured 3d ago against content hash fc8da1c3409d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

azure-mcp-connection 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 3d 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.

msp-claude-plugins/azure-mcp/azure-mcp/skills/connection/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azure MCP Connection

The azure-mcp vendor runs Microsoft's official Azure MCP Server (mcr.microsoft.com/azure-sdk/azure-mcp) as a WYRE-built sidecar inside the MCP gateway. Each connecting MSP supplies its own Azure service principal; the gateway isolates credentials per tenant and scopes every request to the principal you registered.

Anti-triggers

  • Microsoft 365 or Entra ID tenant work — in MSP conversation "Azure tenant" almost always means the M365 tenant. This connector reaches Azure Resource Manager only. Tenant onboarding, GDAP, and CSP relationships are cipp-tenants; Graph app registrations are microsoft-graph-connection.
  • What to actually query once connected — use azure-mcp-observability or azure-mcp-cost-and-capacity.

Read-only deployment — read this first

The gateway runs the Azure MCP Server with the --read-only flag and a deliberately constrained namespace allowlist. Day-one the connector exposes exactly eight read-leaning namespaces:

monitor   pricing   quota   advisor   resourcehealth   applens   subscription   group

Write- and delete-capable namespaces (storage, keyvault, compute, role, aks, and others) are not enabled. This is intentional defense-in-depth: even if a service principal were over-privileged, the gateway cannot route a mutating call. As shipped, azure-mcp is an Azure observability, cost, and resource-health tool — nothing it does changes infrastructure.

Because the deployment is read-only, the service principal you connect should also be read-only. Grant Reader-tier roles and nothing more.

Step 1 — Register an Azure service principal

In the Azure tenant you want to manage, create an Azure AD app registration with a client secret. Either the portal (Microsoft Entra ID → App registrations → New registration) or the CLI works:

az ad sp create-for-rbac \
  --name "wyre-azure-mcp" \
  --role "Reader" \
  --scopes "/subscriptions/<subscription-id>"

Read the full file on GitHub · 112 lines

Changes

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.

  1. 3d ago First seen · 112 lines · 68 tokens per session scan A fc8da1c3409d

Subscribe to this mod's changes

azure-mcp-connection is a skill published in the GitHub repository WYRE-AI/msp-claude-plugins (44 stars, last pushed 4d ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,426 once invoked, about $0.0003 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 2026-09-04.

Related

Other skills, from other repositories

rented-server-setup

Runs an open model in the cloud two ways, and makes the user choose with real numbers. Route A is OVHcloud AI Endpoints, an EU-owned per-token API with zero idle cost, for spiky usage and EU jurisdiction. Route B rents one single-tenant RunPod GPU pod in a region the user picks, serving the model on vLLM behind a…

naveedharri/benai-skills · 258 tokens

allow-team

Puts a running Open WebUI or Odysseus on a shareable public URL through an ngrok tunnel, so a teammate can sign in and use the local models without installing anything. Use when the user says "share Open WebUI with my team", "share Odysseus with my team", "let my colleague use my local AI", "expose Open WebUI", "share…

naveedharri/benai-skills · 181 tokens

gcloud-cli-health-check

Run a Google Cloud CLI (gcloud) health check — verify installation, authentication, active project, recommended region, enabled APIs (run, cloudbuild, artifactregistry, secretmanager, cloudresourcemanager, iam, plus gmail/calendar/monitoring/logging), API access token, billing, IAM bindings, service accounts, and…

MSApps-Mobile/claude-plugins · 175 tokens

dell-idrac-bmc-ops

Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…

dryvist/claude-code-plugins · 111 tokens

homelab-runbooks

Use when powering on a sleeping DR node, converging DNS records for a new ingress vhost, or bringing up OpenBao/Terrakube JWT identity — homelab operational runbooks for power management, DNS, and secrets-engine bring-up.

dryvist/claude-code-plugins · 56 tokens

proxmox-cluster-ops

Operate a Proxmox VE cluster safely — read-only inspection with pvesh/pct/qm/pvecm instead of hand-editing a live guest, node-by-node package updates that respect quorum, and the shape of joining a new node to an existing cluster. Use when inspecting cluster or guest state, planning a rolling update across cluster…

dryvist/claude-code-plugins · 89 tokens