$ ~/registry/skill/composiohq-composio-skills-ai-ml-api-automation

SKILL

ai-ml-api-automation

Name: ai-ml-api-automation
Author: Composio

Automate AI/ML API workflows via Rube MCP, checking latest tool schemas first.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill is an open-source prompt/documentation artifact from a high-trust GitHub source, so its overall risk is relatively low. The main caution is that its workflow depends on external Rube MCP/Composio connections and remote tool execution, so network egress and third-party connection handling should be verified carefully.

CredentialsCaution

The material claims 'no API keys needed,' yet it also requires an ACTIVE `ai_ml_api` connection via `RUBE_MANAGE_CONNECTIONS` and instructs users to complete an auth flow through a returned link. This suggests credentials may be managed through an external connection flow rather than being absent. The skill itself does not appear to collect local secrets, but the scope and storage of third-party tokens should be checked.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube to search tools, manage connections, and execute tools; therefore user requests and tool arguments may be sent to that third-party service. This egress is consistent with the stated functionality, but it conflicts with the metadata claim of 'no remote endpoint host,' so actual data flows and privacy boundaries should be verified before use.

Code executionLow risk

Based on the provided material, this is a prompt/workflow document and does not include runnable local code, install scripts, or logic to spawn local processes. It describes a workflow for calling external MCP tools rather than granting the skill itself local code execution capability.

Data accessLow risk

The material does not show that the skill itself can directly read or write local files, databases, or system resources, nor does it request host data permissions beyond its description. Any substantive data access would mainly occur on the external Rube/Composio tool side, not within this prompt-only skill itself.

Supply chainLow risk

The source is a public GitHub repository with high community adoption (about 64.7k stars), which is a strong positive trust signal; the system also marks it as open-source and prompt-only, giving it good auditability. The missing license declaration and unknown maintenance status are worth noting, but they are not enough to raise this to high risk based on the current evidence.

Recommendations

Before connecting, verify the actual operator of `https://rube.app/mcp`, along with its privacy policy, logging retention, and data handling terms.
Apply least-privilege when authorizing via `RUBE_MANAGE_CONNECTIONS`, and verify what tokens are stored and how they can be revoked.
Avoid sending sensitive business data through this workflow unless the data boundaries of Composio/Rube and downstream AI/ML APIs are clearly confirmed.
Test in an isolated environment first, and log outbound requests and responses for auditability.

Audited by: gpt-5.4 · 2026-06-16

// install

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

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

// download

Download SKILL.mdInstall manifest ↗

// docs

AI ML API Automation via Rube MCP

Automate AI ML API operations through Composio's AI ML API toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/ai_ml_api

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active AI ML API connection via RUBE_MANAGE_CONNECTIONS with toolkit ai_ml_api
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 ai_ml_api
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: "AI ML API 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 AI ML API task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["ai_ml_api"]
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 AI ML API-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `ai_ml_api`
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 Amazon tasks through Rube MCP after checking current tool schemas.

ComposioGet→

$ loading_