bubble-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/bubble-automation --openclawBubble Automation via Rube MCP
Automate Bubble operations through Composio's Bubble toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/bubble
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Bubble connection via
RUBE_MANAGE_CONNECTIONSwith toolkitbubble - Always call
RUBE_SEARCH_TOOLSfirst 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_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitbubble - 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: "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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/bubble-automation/SKILL.mdView on GitHub Overview
Bubble automation orchestration through Composio's Bubble toolkit via Rube MCP. It emphasizes discovering tool schemas with RUBE_SEARCH_TOOLS before executing workflows to ensure compatibility with current Bubble integrations. The approach covers setup, tool discovery, and execution patterns to streamline Bubble operations.
How This Skill Works
It connects to Rube MCP and validates a Bubble connection. It first calls RUBE_SEARCH_TOOLS to fetch current tool schemas, then verifies the connection status via RUBE_MANAGE_CONNECTIONS. Finally, it executes the selected tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug, schema-compliant arguments, and a memory/session structure.
When to Use It
- Starting a new Bubble automation: ensure RUBE_SEARCH_TOOLS responds and the connection is ACTIVE before running any tool.
- Running a discovered Bubble task after tool schemas have been updated to include new fields or changes.
- Executing a multi-step workflow that requires memory and session reuse across steps.
- Handling large tool catalogs by paginating and continuing fetch until all tools are retrieved.
- Performing bulk or chained Bubble operations using multi-execute workflows or remote bench methods.
Quick Start
- Step 1: Configure Rube MCP by adding https://rube.app/mcp as an MCP server in your client; no API keys are required.
- Step 2: Run RUBE_SEARCH_TOOLS to fetch current Bubble tool schemas and pick a tool slug from the results.
- Step 3: Run RUBE_MANAGE_CONNECTIONS for toolkit 'bubble', then execute the tool with RUBE_MULTI_EXECUTE_TOOL using memory and a session_id.
Best Practices
- Always run RUBE_SEARCH_TOOLS first; never hardcode tool slugs or arguments.
- Verify the Bubble connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before execution.
- Use exact field names and types from the tool schemas returned by RUBE_SEARCH_TOOLS.
- Always include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
- Reuse session IDs within a workflow when possible and manage pagination tokens appropriately.
Example Use Cases
- Automate a user signup flow by discovering the appropriate Bubble tool and supplying name and email fields, then executing with a session and memory.
- Sync records to an external CRM by locating a sync tool and passing mapped contact fields retrieved from Bubble.
- Update a record's status after a Bubble query returns results using the exact schema fields from the search output.
- Publish a new Bubble item after validation through the authentication flow, driven by a discovered tool slug.
- Run a batch update across many Bubble records in a single session using memory to coordinate steps.
