Medium Risk

create-fabric-dataflow

Create a new Dataflow Gen2 in Microsoft Fabric workspace

How to control create-fabric-dataflow ↓

AI agents use create-fabric-dataflow 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.

Medium Risk

This tool creates a new dataflow resource in Microsoft Fabric, which is a reversible modification to the workspace. It does not execute arbitrary code, delete data, or move money. While creation can consume resources and affect workspace state, dataflows can be deleted or modified, making this a Write-category risk.

From the tool's definition Tool name is 'create-fabric-dataflow' and description states 'Create a new Dataflow Gen2 in Microsoft Fabric workspace'. The verb 'Create' and the action of instantiating a new resource in a workspace are characteristic Write operations.

Documented attack patterns abuse exactly the kind of access create-fabric-dataflow 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 create-fabric-dataflow:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create-fabric-dataflow": {
      "limits": [
        {
          "counter": "create-fabric-dataflow_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create-fabric-dataflow 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.

  1. Create a free account and register Fabric-Analytics-MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the create-fabric-dataflow tool do? +

Create a new Dataflow Gen2 in Microsoft Fabric workspace. 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.

How do I enforce a policy on create-fabric-dataflow? +

Register the Fabric-Analytics- MCP server in PolicyLayer and add a rule for create-fabric-dataflow: 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.

What risk level is create-fabric-dataflow? +

create-fabric-dataflow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create-fabric-dataflow? +

Yes. Add a rate_limit block to the create-fabric-dataflow 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.

How do I block create-fabric-dataflow completely? +

Set action: deny in the PolicyLayer policy for create-fabric-dataflow. 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.

What MCP server provides create-fabric-dataflow? +

create-fabric-dataflow 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.

Enforce policy on every Fabric-Analytics-MCP tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.