// SCAN REPORT

Dataiku DSS MCP Server

43 tools. 19 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

19 can modify or destroy data

24 read-only

43 tools total

Community server · catalogue entry verified 30/06/2026

How to control Dataiku DSS MCP Server ↓

TOOL MAP

What Dataiku DSS MCP Server exposes to your agents

Read (24) Write / Execute (14) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Dataiku DSS MCP Server tools

Destructive · High clear_dataset Clearing a dataset removes data irreversibly and cannot be undone without restoration from backups. Destructive · High delete_dataset Deletion of datasets cannot be undone and represents permanent loss of data. Destructive · High delete_recipe Deleting a recipe is a destructive operation that cannot be undone without restoration from backups. Destructive · High delete_scenario Deleting a scenario permanently removes a potentially critical automation or workflow component from a Dataiku project.

19 of Dataiku DSS MCP Server's 43 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dataiku DSS MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Dataiku DSS MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_dataset": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_scenario_trigger": {
    "limits": [
      {
        "counter": "add_scenario_trigger_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_dataset_metrics": {
    "limits": [
      {
        "counter": "check_dataset_metrics_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Dataiku DSS MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DATAIKU DSS →

Instant setup, no code required.

FULL CATALOGUE

All 43 Dataiku DSS MCP Server tools

DESTRUCTIVE 5 tools

Destructive clear_dataset Clear data from a dataset Destructive delete_dataset Delete a dataset from a project Destructive delete_recipe Delete a recipe from a project Destructive delete_scenario Delete a scenario from a project Destructive remove_scenario_trigger Remove a trigger from a scenario

EXECUTE 4 tools

Execute build_dataset Build a dataset Execute cancel_running_jobs Cancel running jobs/scenarios Execute run_recipe Run a recipe to build its outputs Execute run_scenario Run a scenario manually

WRITE 10 tools

Write add_scenario_trigger Add a trigger to a scenario Write batch_update_objects Update multiple objects with similar changes Write clone_scenario Clone an existing scenario with modifications Write create_dataset Create a new dataset in a project Write create_recipe Create a new recipe in a Dataiku project Write create_scenario Create a new scenario in a project Write duplicate_project_structure Copy project structure to new project Write update_dataset Update dataset settings Write update_recipe Update an existing recipe Write update_scenario Update scenario settings

READ 24 tools

Read check_dataset_metrics Get latest dataset metrics Read export_project_config Export project configuration as JSON/YAML Read get_code_environments List available Python/R environments Read get_connections List available data connections Read get_dataset_info Get detailed information about a dataset Read get_dataset_sample Get sample data from datasets Read get_job_details Get detailed job execution information Read get_project_flow Get complete data flow/pipeline structure Read get_project_variables Get project-level variables and configuration Read get_recent_runs Get recent run history across all scenarios/recipes Read get_recipe_code Extract actual Python/SQL code from recipes Read get_recipe_info Get detailed information about a recipe Read get_scenario_info Get detailed information about a scenario Read get_scenario_logs Get detailed run logs and error messages for failed scenarios Read get_scenario_run_history Get run history for a scenario Read get_scenario_steps Get step configuration including Python code Read inspect_dataset_schema Get dataset schema information Read list_datasets List all datasets in a project Read list_projects List all available Dataiku projects Read list_recipes List all recipes in a project Read list_scenarios List all scenarios in a project Read search_project_objects Search for datasets, recipes, scenarios by name/pattern Read test_recipe_dry_run Test recipe logic without actual execution Read validate_recipe_syntax Validate Python/SQL syntax of a recipe

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Dataiku DSS MCP Server

Can an AI agent delete data through the Dataiku DSS MCP Server MCP server? +

Yes. The Dataiku DSS MCP Server server exposes 5 destructive tools including clear_dataset, delete_dataset, delete_recipe. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Dataiku DSS MCP Server? +

The Dataiku DSS MCP Server server has 10 write tools including add_scenario_trigger, batch_update_objects, clone_scenario. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Dataiku DSS MCP Server.

How many tools does the Dataiku DSS MCP Server MCP server expose? +

43 tools across 4 categories: Destructive, Execute, Read, Write. 24 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on Dataiku DSS MCP Server? +

Register the Dataiku DSS MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Dataiku DSS MCP Server tool call.

Deterministic rules across all 43 Dataiku DSS MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DATAIKU DSS →

Instant setup, no code required.

43 Dataiku DSS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.