AI agents invoke start_pipeline_update 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 a data pipeline, which is an external operation whose consequences depend on pipeline logic and arguments. While not destructive by itself, it executes transformations and processes data at scale, making it Execute rather than Write. The high severity reflects the potential for unintended data processing or resource consumption if triggered inappropriately by an AI agent.
From the tool's definition 'Start a DLT pipeline update' initiates an external operation (Databricks DLT pipeline execution) whose effects depend on pipeline configuration and data transformations. DLT pipelines perform ETL operations that execute code and transform data.
Documented attack patterns abuse exactly the kind of access start_pipeline_update 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 start_pipeline_update:
{
"version": "1",
"default": "deny",
"tools": {
"start_pipeline_update": {
"limits": [
{
"counter": "start_pipeline_update_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_pipeline_update 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.
Start a DLT pipeline update. 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 start_pipeline_update: 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.
start_pipeline_update 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 start_pipeline_update 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 start_pipeline_update. 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.
start_pipeline_update is provided by the Databricks MCP Server MCP server (pulkitxchadha/awesome-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.
86 Databricks MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.