What is RUBE MCP and how do I set it up?

RUBE MCP is a centralized machine control protocol. Add https://rube.app/mcp as an MCP server in your client; no API keys are needed.

Do I always need to call RUBE_SEARCH_TOOLS before running a workflow?

Yes. RUBE_SEARCH_TOOLS fetches current tool slugs and input schemas to ensure you use up-to-date configurations.

How can I ensure safe execution of tools?

Ensure the Everhour connection is ACTIVE, use exact schema field names and types from search results, and include a non-empty memory object in RUBE_MULTI_EXECUTE_TOOL calls along with a valid session_id.

everhour-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Everhour Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/everhour

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Everhour operations using Composio's Everhour toolkit via Rube MCP. This approach emphasizes discovering current tool schemas first and ensuring an active Everhour connection before executing any workflows.

How This Skill Works

Tools are discovered with RUBE_SEARCH_TOOLS to obtain up to date slugs and input schemas. You then verify the Everhour connection with RUBE_MANAGE_CONNECTIONS and execute chosen tools via RUBE_MULTI_EXECUTE_TOOL, including the memory object and an existing session_id.

When to Use It

You want to perform an Everhour operation but must start by fetching current tool schemas with RUBE_SEARCH_TOOLS.
You need to verify that the Everhour connection is ACTIVE before running workflows.
You are executing a tool using the slug and exact field names from the schema.
You want to reuse a session ID across a workflow to maintain context.
You are performing bulk operations or multiple tool invocations with RUBE_REMOTE_WORKBENCH.

Quick Start

Step 1: Add RUBE MCP endpoint https://rube.app/mcp to your client configuration and verify connectivity with RUBE_SEARCH_TOOLS.
Step 2: Use RUBE_MANAGE_CONNECTIONS with toolkit everhour to establish or verify an ACTIVE connection.
Step 3: Discover tools, then execute with RUBE_MULTI_EXECUTE_TOOL including memory and a valid session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before any workflow to get current tool schemas.
Check the connection is ACTIVE with RUBE_MANAGE_CONNECTIONS before executing tools.
Use exact field names and types from the tool schema; avoid hardcoding slugs or arguments.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls even if empty ({})
Reuse session IDs where possible and manage pagination tokens for complete results

Example Use Cases

Example 1: Discover tools for Everhour operations with RUBE_SEARCH_TOOLS, select a tool slug from the results, then prepare to run it.
Example 2: Connect to Everhour via RUBE_MANAGE_CONNECTIONS with toolkit everhour and confirm the ACTIVE status before execution.
Example 3: Execute a discovered Everhour tool using RUBE_MULTI_EXECUTE_TOOL, passing in exact schema fields and a non-empty memory object.
Example 4: Retrieve updated tool schemas using RUBE_GET_TOOL_SCHEMAS to adjust to changes in tool inputs before running workflows.
Example 5: Perform bulk operations on multiple Everhour tasks using RUBE_REMOTE_WORKBENCH with run_composio_tool for efficiency.

Frequently Asked Questions

Add this skill to your agents