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

backendless-automation skill

/backendless-automation

This skill automates Backendless tasks via Rube MCP, continuously discovering current tool schemas before execution to ensure up-to-date workflows.

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

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

Files (1)
SKILL.md
2.9 KB
---
name: backendless-automation
description: "Automate Backendless tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Backendless Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["backendless"]
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 Backendless-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `backendless` |
| 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 Backendless tasks through Composio's Backendless toolkit using Rube MCP. It provides a repeatable pattern for discovering tools, verifying connections, and executing operations programmatically. The skill emphasizes always searching tools first to avoid schema drift and ensuring connection health before runs.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to discover available Backendless tool slugs, input schemas, and recommended execution plans. It then validates or establishes a Backendless connection via RUBE_MANAGE_CONNECTIONS and runs operations with RUBE_MULTI_EXECUTE_TOOL (including an explicit memory object and session_id). For bulk or complex flows, it supports RUBE_REMOTE_WORKBENCH and schema retrieval via RUBE_GET_TOOL_SCHEMAS.

When to use it

  • Perform CRUD operations or admin tasks against Backendless programmatically.
  • Automate repeatable backend workflows that require up-to-date tool schemas.
  • Run bulk operations or orchestrated sequences across Backendless services.
  • Recover or re-run partial workflows while preserving session context.
  • Integrate Backendless steps into larger Composio/Rube-driven automation.

Best practices

  • Always call RUBE_SEARCH_TOOLS at the start of any workflow to fetch current tool schemas and slugs.
  • Check RUBE_MANAGE_CONNECTIONS for toolkit 'backendless' and confirm ACTIVE status before executing tools.
  • Include a memory object (even empty {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session_id for the workflow.
  • Never hardcode tool slugs or argument shapes — use the exact field names and types returned by search.
  • Handle pagination in responses: follow pagination tokens and continue fetching until complete.

Example use cases

  • Provision new data tables and set permissions in Backendless by discovering the right tool and executing create-table operations.
  • Run scheduled data migrations: discover bulk-update tools, confirm connection, then execute with RUBE_REMOTE_WORKBENCH.
  • Automate user onboarding flows that create records, set user roles, and provision resources in a single session.
  • Build a CI/CD step that validates Backendless schemas by calling RUBE_GET_TOOL_SCHEMAS before deployment.
  • Recover failed workflows by reusing the original session_id and replaying missing RUBE_MULTI_EXECUTE_TOOL steps.

FAQ

What must I do before executing any tool?

Always call RUBE_SEARCH_TOOLS to get current tool slugs and schemas, then confirm the Backendless connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.

Can I hardcode tool slugs and argument shapes?

No. Tool schemas change; hardcoding leads to failures. Use the search results for exact field names and types.