run_job

THE RISK

High Risk

Why run_job needs a policy

This tool triggers external operations (Databricks job execution) whose side effects are determined by the job configuration and supplied arguments. While not immediately destructive, a misused job_id or malicious parameters could cause significant data processing, resource consumption, or unintended transformations.

From the tool's definition Tool name 'run_job' combined with description 'Run a Databricks job' indicates execution of a job with specified parameters.

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

POLICY

How to control run_job

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_job:

policy.json

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

run_job 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.

Create a free account and register Databricks MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Databricks MCP Server tools

Destructive terminate_cluster Terminate a Databricks cluster with parameter: cluster_id (required) Execute execute_sql Execute a SQL statement with parameters: statement (required), warehouse_id (required), ca Execute start_cluster Start a terminated Databricks cluster with parameter: cluster_id (required) Write create_cluster Create a new Databricks cluster with parameters: cluster_name (required), spark_version (r Read get_cluster Get information about a specific Databricks cluster with parameter: cluster_id (required) Read list_clusters List all Databricks clusters Read list_files List files and directories in a DBFS path with parameter: dbfs_path (required) Read list_jobs List all Databricks jobs

All 11 Databricks MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Databricks MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_job

What does the run_job tool do? +

Run a Databricks job with parameters: job_id (required), notebook_params (optional). 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.

How do I enforce a policy on run_job? +

Register the Databricks MCP Server MCP server in PolicyLayer and add a rule for run_job: 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.

What risk level is run_job? +

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

Can I rate-limit run_job? +

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

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

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

Enforce policy on every Databricks MCP Server tool call.

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.

CHECK YOUR STACK →