call_databricks_tool · Databricks MCP Proxy MCP

WHAT IT DOES

What call_databricks_tool does on Databricks MCP Proxy

AI agents invoke call_databricks_tool to trigger actions in Databricks MCP Proxy. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why call_databricks_tool needs a policy

This tool acts as a proxy that can invoke any tool available on a remote Databricks MCP server. Since the set of tools it can call is unbounded and potentially includes destructive, financial, or code-execution operations, it must be classified at the most severe applicable category.

From the tool's definition 'Call a tool on the remote Databricks MCP server' — executes arbitrary remote tools on a Databricks MCP server

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_databricks_tool Rate-limited

call_databricks_tool stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "call_databricks_tool": {
      "limits": [
        {
          "counter": "call_databricks_tool_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Databricks MCP Proxy, so you can run agents against it safely.

FAQ

Questions about call_databricks_tool

What does the call_databricks_tool tool do? +

Call a tool on the remote Databricks MCP server. It is categorised as a Execute tool in the Databricks MCP Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on call_databricks_tool? +

Register the Databricks MCP Proxy MCP server in PolicyLayer and add a rule for call_databricks_tool: 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 Databricks MCP Proxy. Nothing to install.

What risk level is call_databricks_tool? +

call_databricks_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit call_databricks_tool? +

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

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

call_databricks_tool is provided by the Databricks MCP Proxy MCP server (smaheshwari-ux/databricks-mcp-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.