AI agents use fabric_create_lakehouse to create or update resources in Fabric-Analytics-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fabric-Analytics-MCP environment.
The tool creates a new lakehouse resource, which is a reversible write operation. While the description is empty, the tool name is explicit: 'create' is a Write category verb, and lakehouses are persistent data storage constructs in Fabric.
From the tool's definition Tool name 'fabric_create_lakehouse' indicates creation of a lakehouse resource in Microsoft Fabric. The 'create' verb combined with 'lakehouse' (a data storage artifact) clearly signals a write operation that creates new infrastructure.
Documented attack patterns abuse exactly the kind of access fabric_create_lakehouse gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fabric-Analytics-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for fabric_create_lakehouse:
{
"version": "1",
"default": "deny",
"tools": {
"fabric_create_lakehouse": {
"limits": [
{
"counter": "fabric_create_lakehouse_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}fabric_create_lakehouse 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.
fabric_create_lakehouse. It is categorised as a Write tool in the Fabric-Analytics-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fabric-Analytics- MCP server in PolicyLayer and add a rule for fabric_create_lakehouse: 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 Fabric-Analytics-MCP. Nothing to install.
fabric_create_lakehouse 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 fabric_create_lakehouse 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 fabric_create_lakehouse. 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.
fabric_create_lakehouse is provided by the Fabric-Analytics- MCP server (santhoshravindran7/fabric-analytics-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 83 Fabric-Analytics-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
83 Fabric-Analytics-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.