Do I need API keys to use Rube MCP with 21risk?

No API keys are needed — just add the MCP endpoint and connect.

What if tool schemas change or I see missing fields?

Always run RUBE_SEARCH_TOOLS to fetch current schemas and use exact field names from the results; avoid hardcoding.

How should I handle sessions and memory during workflows?

Reuse session IDs within a workflow; generate new ones for new workflows. Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.

-21risk-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/-21risk-automation --openclaw

Files (1)

SKILL.md

2.8 KB

21risk Automation via Rube MCP

Automate 21risk operations through Composio's 21risk toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/_21risk

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active 21risk connection via RUBE_MANAGE_CONNECTIONS with toolkit _21risk
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 _21risk
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: "21risk 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 21risk task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["_21risk"]
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 21risk-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `_21risk`
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/-21risk-automation/SKILL.mdView on GitHub

Overview

Automates 21risk operations through Composio's 21risk toolkit via Rube MCP. Requires a connected Rube MCP and an active 21risk setup, and you must always fetch current tool schemas with RUBE_SEARCH_TOOLS before any workflow.

How This Skill Works

Starter: connect Rube MCP and verify tools exist with RUBE_SEARCH_TOOLS. Then manage the 21risk toolkit connection with RUBE_MANAGE_CONNECTIONS and run tools using RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug and a memory payload. Always reuse session IDs within a workflow and include memory in every multi-execute call to align with the schema-driven inputs.

When to Use It

When automating a 21risk operation and you need to use the latest tool schemas discovered by RUBE_SEARCH_TOOLS.
When you must ensure the Rube MCP connection for _21risk is ACTIVE before executing any workflow.
When iterating across multiple 21risk tasks within a single session to optimize throughput.
When tool schemas may change and you want to avoid hardcoding slugs or arguments.
When performing bulk or chained operations that require RUBE_MULTI_EXECUTE_TOOL and careful memory handling.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
Step 2: Verify RUBE_SEARCH_TOOLS responds to confirm tool availability.
Step 3: Manage connections for toolkit _21risk, discover a tool slug, then execute via RUBE_MULTI_EXECUTE_TOOL with memory and a session_id.

Best Practices

Always search for tool schemas first with RUBE_SEARCH_TOOLS to get current slugs and inputs.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before running tools.
Use exact field names and types from the search results; avoid hardcoding.
Always include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow; generate new ones only for separate workflows and monitor pagination tokens.

Example Use Cases

Automate a single 21risk task by discovering the appropriate tool, ensuring ACTIVE connection, and executing with a memory payload.
Batch several 21risk tasks in a single session by discovering multiple tool slugs and executing them sequentially via RUBE_MULTI_EXECUTE_TOOL.
Handle tool schema changes gracefully by re-running RUBE_SEARCH_TOOLS before each batch of executions.
Reuse a session across related 21risk tasks to improve throughput and reduce setup steps.
Inspect detailed tool schemas using RUBE_GET_TOOL_SCHEMAS to validate expected inputs before execution.

Frequently Asked Questions

Add this skill to your agents