Do I need API keys to use this skill?

No API keys are required. Add the MCP endpoint and it works.

How do I discover available tools?

Run RUBE_SEARCH_TOOLS with a Pushbullet use case to fetch tool slugs, input schemas, and execution plans.

What if the Pushbullet connection is not ACTIVE?

Use RUBE_MANAGE_CONNECTIONS to connect; if the response provides an auth link, follow it and recheck until ACTIVE.

pushbullet-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Pushbullet Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/pushbullet

Prerequisites

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

Step 2: Check Connection

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

Overview

Pushbullet Automation via Rube MCP lets you orchestrate Pushbullet tasks using Composio's toolkit. It emphasizes always querying RUBE_SEARCH_TOOLS for current tool schemas before running workflows and ensuring an ACTIVE Pushbullet connection before execution.

How This Skill Works

First, discover available tools with RUBE_SEARCH_TOOLS to fetch tool slugs and input schemas. Then verify the Pushbullet connection with RUBE_MANAGE_CONNECTIONS and finally execute selected tools with RUBE_MULTI_EXECUTE_TOOL, including a memory payload. The workflow pattern repeats per task.

When to Use It

Setting up a Pushbullet automation workflow with Rube MCP
When you need current tool schemas before invocation
When you must verify an ACTIVE Pushbullet connection prior to any tool run
When you want to run discovered tools in a single session using RUBE_MULTI_EXECUTE_TOOL
When you need to avoid hardcoding tool slugs by re-searching tools before each run

Quick Start

Step 1: Add the Rube MCP server at https://rube.app/mcp in your client config and verify RUBE_SEARCH_TOOLS responds
Step 2: Connect the Pushbullet toolkit via RUBE_MANAGE_CONNECTIONS and ensure the status becomes ACTIVE
Step 3: Discover tools with RUBE_SEARCH_TOOLS and execute a selected tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and memory payload

Best Practices

Always run RUBE_SEARCH_TOOLS before workflow execution to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Use exact field names and types from the search results; avoid hardcoding
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs within a workflow and generate new ones for new workflows

Example Use Cases

Discover Pushbullet operations with RUBE_SEARCH_TOOLS, then send a note using RUBE_MULTI_EXECUTE_TOOL with the chosen slug and message.
Check the connection status via RUBE_MANAGE_CONNECTIONS and re-auth if the status is not ACTIVE before sending a notification.
Send multiple Pushbullet notifications in a single workflow by looping through tool slugs and supplying memory data for each call.
Update automation when tool schemas change by re-running RUBE_SEARCH_TOOLS and adapting slugs without hardcoding.
Paginate through tool schemas with RUBE_GET_TOOL_SCHEMAS to discover all available Pushbullet tools.

Frequently Asked Questions

Add this skill to your agents