$ ~/registry/skill/composiohq-composio-skills-datarobot-automation

SKILL

datarobot-automation

Name: datarobot-automation
Author: Composio

Automate DataRobot tasks through Rube MCP for faster model and data workflows.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.9k

Summary

This skill itself is open-source prompt/documentation content with no direct local secret requirement and no embedded executable code. However, it is designed to route usage through remote Rube MCP/Composio and DataRobot connections, so actual use involves outbound connectivity, third-party authorization, and remote tool invocation, making it a low-to-moderate concern rather than high risk.

CredentialsCaution

The material claims 'no API keys needed,' but it also requires creating a `datarobot` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth link, which indicates third-party authorization or tokens are still involved even if not exposed in the skill config. No explicit credential-stealing behavior is described, but scopes should be limited to the minimum required for DataRobot.

Network egressCaution

The README explicitly instructs adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube to discover and execute DataRobot tools. Therefore, task arguments, session identifiers, and some business data may transit through a third-party service. No obviously unrelated or suspicious egress endpoints are listed, but standard third-party network exposure exists.

Code executionLow risk

Based on the material, this is a prompt-only skill description with no local scripts, install commands, or instructions to directly execute code on the host. The referenced `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` are descriptions of remote tool orchestration, not local execution privileges granted by this skill itself.

Data accessCaution

The stated purpose is to 'Automate Datarobot operations,' which implies potential access to or modification of projects, jobs, or related business data in DataRobot during actual use. The material does not state that it reads the local filesystem, and no local data permissions beyond its stated purpose are requested. The main concern is the scope of remote business-data access, which should be controlled by the connected account's permissions.

Supply chainLow risk

The source is an open-source GitHub repository with high community adoption (~64.9k stars), and the system marks it as open-source and prompt-only, which supports auditability. Although the license is unspecified and maintenance status is unknown, the current material shows no closed-source delivery, obfuscated installation, or clear supply-chain red flags; source credibility materially lowers the risk.

Recommendations

Only connect to `https://rube.app/mcp` if it is approved by your organization, and review its privacy, logging, and data-handling terms.
Use a least-privilege DataRobot account for the connection, avoiding unnecessary write or admin permissions.
Before executing any tool, verify the tool names, schemas, and intended actions returned by `RUBE_SEARCH_TOOLS` to avoid invoking high-privilege operations by mistake.
Do not send unnecessary sensitive data through this path; for production data, first validate the third-party transit path and auditability.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "datarobot-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/datarobot-automation/SKILL.md
2. Save it as ~/.claude/skills/datarobot-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Datarobot Automation via Rube MCP

Automate Datarobot operations through Composio's Datarobot toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/datarobot

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Datarobot connection via RUBE_MANAGE_CONNECTIONS with toolkit datarobot
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit datarobot
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Datarobot operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Datarobot task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["datarobot"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Datarobot-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `datarobot`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Automate BigML tasks and machine learning workflows through Rube MCP.

ComposioGet→

$ loading_