mcp_upload_notebook
AI agents use mcp_upload_notebook to create or update resources in Databricks MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Databricks MCP Server environment.
Upload operations create or modify data (notebooks stored in Databricks workspace) reversibly. This is a Write category action. Severity is medium because uploaded notebooks could be executed by jobs/pipelines (Execute risk), but the tool itself only creates/modifies the artifact, not immediately executing it.
From the tool's definition Tool name 'mcp_upload_notebook' indicates file upload operation. Server description mentions 'interact with Databricks clusters, jobs, and DLT pipelines' and sibling tools include 'mcp_create_and_run_job_for_notebook' and 'mcp_create_dlt_pipeline', suggesting…
Attacks that exploit this kind of access
mcp_upload_notebook. It is categorised as a Write tool in the Databricks MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for mcp_upload_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.
mcp_upload_notebook 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 mcp_upload_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 mcp_upload_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.
mcp_upload_notebook is provided by the Databricks MCP Server MCP server (stephenjhsu/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →