AI agents invoke run_notebook to trigger actions in Databricks MCP Server. 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.
This tool triggers execution of external code (a Databricks notebook) whose side effects are unpredictable and depend entirely on the notebook's logic. It is not a simple read operation, nor is it reversible in the sense of Execute category—it runs code that could modify data, trigger jobs, or interact with external systems.
From the tool's definition Tool name 'run_notebook' and description 'Submit a one-time notebook run' indicates execution of arbitrary code stored in Databricks notebooks.
Documented attack patterns abuse exactly the kind of access run_notebook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Databricks MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_notebook:
{
"version": "1",
"default": "deny",
"tools": {
"run_notebook": {
"limits": [
{
"counter": "run_notebook_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_notebook 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.
Free to start. No card required.
Submit a one-time notebook run. It is categorised as a Execute tool in the Databricks MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for run_notebook: 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 Server. Nothing to install.
run_notebook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_notebook 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 run_notebook. 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.
run_notebook is provided by the Databricks MCP Server MCP server (markov-kernel/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Databricks 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.
38 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.