Do I need API keys to use Kraken IO automation?

No API keys are needed. Add the Rube MCP endpoint and use the Kraken IO toolkit via Composio; all authentication is handled through the MCP connection flow.

What if tool schemas change?

Always call RUBE_SEARCH_TOOLS to fetch current tool slugs and input schemas. Do not hardcode slugs or argument names.

How do I know the Kraken IO connection is ready?

Check RUBE_MANAGE_CONNECTIONS for an ACTIVE status. If not ACTIVE, follow the returned auth link to complete setup and recheck.

kraken-io-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/kraken-io-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Kraken IO Automation via Rube MCP

Automate Kraken IO operations through Composio's Kraken IO toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/kraken_io

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Kraken IO connection via RUBE_MANAGE_CONNECTIONS with toolkit kraken_io
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 kraken_io
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: "Kraken IO 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 Kraken IO task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["kraken_io"]
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 Kraken IO-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `kraken_io`
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

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/kraken-io-automation/SKILL.mdView on GitHub

Overview

This skill automates Kraken IO operations using Composio's Kraken IO toolkit through Rube MCP. It emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before executing workflows and requires an ACTIVE Kraken IO connection managed via RUBE_MANAGE_CONNECTIONS.

How This Skill Works

Set up by adding the Rube MCP endpoint, then verify RUBE_SEARCH_TOOLS. Discover available Kraken IO tools and their input schemas, establish or validate an ACTIVE Kraken IO connection with RUBE_MANAGE_CONNECTIONS, and finally execute tools using RUBE_MULTI_EXECUTE_TOOL with a session_id and memory payload. Always reference the latest schemas from tool discovery rather than hardcoding slugs or fields.

When to Use It

When you need to automate Kraken IO operations and keep tool schemas current
When you need to establish or verify a Kraken IO connection via RUBE_MANAGE_CONNECTIONS before tasks
When performing a sequence of tools in a single workflow and reusing a session_id
When executing batch Kraken IO tasks via RUBE_REMOTE_WORKBENCH for bulk operations
When you want to fetch the latest tool schemas with RUBE_GET_TOOL_SCHEMAS to adapt inputs

Quick Start

Step 1: Configure Rube MCP endpoint (https://rube.app/mcp) and verify RUBE_SEARCH_TOOLS responds
Step 2: Discover Kraken IO tools with RUBE_SEARCH_TOOLS using the use_case 'Kraken IO operations' to fetch slugs and schemas
Step 3: Ensure ACTIVE connection with RUBE_MANAGE_CONNECTIONS, then run a tool via RUBE_MULTI_EXECUTE_TOOL using a discovered slug and memory while reusing a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to get current tool slugs and schemas
Confirm the Kraken IO connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools
Use exact field names and types from the search results; avoid hardcoding
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and paginate responses if provided

Example Use Cases

Daily balance check: Discover tools with RUBE_SEARCH_TOOLS, connect to Kraken IO, and run a get_balance tool in a single session
Batch orders: In one session, discover order-related tools and execute multiple tools with RUBE_MULTI_EXECUTE_TOOL, reusing memory and session_id
Reconnect and verify: If the connection shows not ACTIVE, follow the auth flow and re-validate before high-risk tasks
Bulk Kraken IO tasks: Use RUBE_REMOTE_WORKBENCH to run a batch of Kraken IO tasks via run_composio_tool()
Schema refresh: Use RUBE_GET_TOOL_SCHEMAS to pull the latest tool schemas and adapt automation inputs

Frequently Asked Questions

Add this skill to your agents