Low Risk

databricks_cost_estimate

Estimate monthly and annual Azure Databricks costs based on DBU consumption.

How to control databricks_cost_estimate ↓

What databricks_cost_estimate does on Azure Pricing MCP Server

AI agents call databricks_cost_estimate to retrieve information from Azure Pricing MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why databricks_cost_estimate needs a policy

This tool reads pricing data and performs calculations to generate cost estimates. It is purely informational with no capability to execute commands, modify infrastructure, delete data, or commit financial transactions. The tool enables cost visibility and planning but does not actually provision resources, modify configurations, or transfer funds.

From the tool's definition Tool performs 'Estimate monthly and annual Azure Databricks costs based on DBU consumption' — a calculation/estimation function that retrieves and presents pricing information without modifying any data, systems, or configurations. No side effects.

Documented attack patterns abuse exactly the kind of access databricks_cost_estimate gives an agent:

How to control databricks_cost_estimate

PolicyLayer is an MCP gateway — it sits between your AI agents and Azure Pricing MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for databricks_cost_estimate:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "databricks_cost_estimate": {}
  }
}

databricks_cost_estimate is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Azure Pricing MCP Server — 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about databricks_cost_estimate

What does the databricks_cost_estimate tool do? +

Estimate monthly and annual Azure Databricks costs based on DBU consumption. It is categorised as a Read tool in the Azure Pricing MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on databricks_cost_estimate? +

Register the Azure Pricing MCP Server MCP server in PolicyLayer and add a rule for databricks_cost_estimate: 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 Pricing MCP Server. Nothing to install.

What risk level is databricks_cost_estimate? +

databricks_cost_estimate is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit databricks_cost_estimate? +

Yes. Add a rate_limit block to the databricks_cost_estimate 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 databricks_cost_estimate completely? +

Set action: deny in the PolicyLayer policy for databricks_cost_estimate. 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 databricks_cost_estimate? +

databricks_cost_estimate is provided by the Azure Pricing MCP Server MCP server (msftnadavbh/azurepricingmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Azure Pricing MCP Server tool call.

Start from Azure Pricing 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.

18 Azure Pricing MCP Server tools catalogued and risk-classified — across an index of 43,000+ 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.