home / skills / composiohq / awesome-claude-skills / bubble-automation

bubble-automation skill

safe

/bubble-automation

This skill automates Bubble tasks via Rube MCP, leveraging tool discovery to execute current Bubble workflows safely and efficiently.

npx playbooks add skill composiohq/awesome-claude-skills --skill bubble-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.8 KB

---
name: bubble-automation
description: "Automate Bubble tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Bubble Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/bubble](https://composio.dev/toolkits/bubble)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Bubble connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `bubble`
- 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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `bubble`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Bubble 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 Bubble task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["bubble"]
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 Bubble-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `bubble` |
| 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](https://composio.dev)*

Overview

This skill automates Bubble.io tasks by orchestrating Composio’s Bubble toolkit through the Rube MCP interface. It guides discovery of current tool schemas, ensures active Bubble connections, and runs schema-compliant tool executions. The workflow emphasizes searching tools first and managing sessions and memory correctly.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve available Bubble tool slugs, input schemas, recommended plans, and pagination tokens. It then verifies or establishes a Bubble connection via RUBE_MANAGE_CONNECTIONS and uses RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk ops) to run one or more discovered tools with memory and a session ID. Always follow the returned schema fields exactly and reuse session IDs within a workflow.

When to use it

Automate CRUD operations or workflows in a Bubble app from an agent
Integrate Bubble tasks into a larger automated workflow or CI pipeline
Perform bulk operations using RUBE_REMOTE_WORKBENCH and run_composio_tool()
When you need up-to-date tool schemas before executing actions
When you must ensure the Bubble connection is authenticated and active before running tasks

Best practices

Always call RUBE_SEARCH_TOOLS first to get current tool slugs and input schemas
Verify toolkit connection with RUBE_MANAGE_CONNECTIONS and confirm ACTIVE status before execution
Provide the memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session_id across steps in the same workflow; generate a new session for new workflows
Follow exact field names and types from the search response; do not hardcode arguments

Example use cases

Update database records in Bubble by discovering the correct update tool and passing schema-compliant fields
Bulk import user data into Bubble using RUBE_REMOTE_WORKBENCH and run_composio_tool()
Trigger a sequence of Bubble API workflows from an agent after confirming active connection and tool schemas
Fetch form field schemas with RUBE_GET_TOOL_SCHEMAS to build a dynamic UI or validation logic before submitting data
Paginate through a large list of Bubble resources by following pagination tokens returned by searches

FAQ

Do I need API keys to use Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client; no API keys are required for basic MCP access.

What if a tool schema changes mid-workflow?

Always call RUBE_SEARCH_TOOLS before executing tools. If schemas change, fetch them again, update arguments to match, and continue with a current session_id.