AI agents use select-tenant to create or update resources in Azure MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Azure MCP Server environment.
Selecting a tenant and subscription changes the active context/session state for subsequent Azure operations. This is a Write-level action as it modifies the working configuration, but it doesn't directly create, destroy, or move resources.
From the tool's definition 'Select Azure tenant and subscription' — sets/changes the active tenant and subscription context
Documented attack patterns abuse exactly the kind of access select-tenant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Azure MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for select-tenant:
{
"version": "1",
"default": "deny",
"tools": {
"select-tenant": {
"limits": [
{
"counter": "select-tenant_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}select-tenant stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Select Azure tenant and subscription. It is categorised as a Write tool in the Azure MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Azure MCP Server MCP server in PolicyLayer and add a rule for select-tenant: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Azure MCP Server. Nothing to install.
select-tenant is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the select-tenant rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for select-tenant. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
select-tenant is provided by the Azure MCP Server MCP server (kalivaraprasad-gonapa/azure-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Azure MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Azure MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.