run_recipe · Dataiku DSS MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_recipe does on Dataiku DSS MCP Server

AI agents invoke run_recipe to trigger actions in Dataiku DSS 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.

WHY IT NEEDS A POLICY

Why run_recipe needs a policy

This tool executes a pre-defined recipe within Dataiku DSS to produce data outputs. While the recipe itself is typically pre-built and not arbitrary code, execution of recipes can produce significant side effects on datasets and workflows. The severity is high because a misconfigured or malicious recipe execution could corrupt data, consume significant computational resources, or trigger downstream process failures.

From the tool's definition The tool description states 'Run a recipe to build its outputs' which indicates execution of a defined data processing operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_recipe Rate-limited

run_recipe 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": {
    "run_recipe": {
      "limits": [
        {
          "counter": "run_recipe_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 Dataiku DSS MCP Server, so you can run agents against it safely.

FAQ

Questions about run_recipe

What does the run_recipe tool do? +

Run a recipe to build its outputs. It is categorised as a Execute tool in the Dataiku DSS 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_recipe? +

Register the Dataiku DSS MCP Server MCP server in PolicyLayer and add a rule for run_recipe: 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 Dataiku DSS MCP Server. Nothing to install.

What risk level is run_recipe? +

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

Can I rate-limit run_recipe? +

Yes. Add a rate_limit block to the run_recipe 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_recipe completely? +

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

run_recipe is provided by the Dataiku DSS MCP Server MCP server (steven0lisa/mcp-dataiku). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.