home / skills / composiohq / awesome-claude-skills / salesforce-service-cloud-automation

salesforce-service-cloud-automation skill

/salesforce-service-cloud-automation

This skill automates Salesforce Service Cloud tasks using Composio's Rube MCP toolkit, discovering tools first and ensuring active connections.

npx playbooks add skill composiohq/awesome-claude-skills --skill salesforce-service-cloud-automation

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

Files (1)
SKILL.md
3.1 KB
---
name: salesforce-service-cloud-automation
description: "Automate Salesforce Service Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Salesforce Service Cloud Automation via Rube MCP

Automate Salesforce Service Cloud operations through Composio's Salesforce Service Cloud toolkit via Rube MCP.

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["salesforce_service_cloud"]
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 Salesforce Service Cloud-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `salesforce_service_cloud` |
| 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 Salesforce Service Cloud tasks through Composio’s Salesforce Service Cloud toolkit using Rube MCP. It provides a repeatable pattern for discovering tools, validating connections, and executing toolkit actions while enforcing schema compliance and session management. The skill is designed for reliable, production-ready automation of cases, contacts, and bulk operations in Salesforce Service Cloud.

How this skill works

The skill first queries Rube MCP with RUBE_SEARCH_TOOLS to retrieve the current tool catalog and input schemas for Salesforce Service Cloud operations. It then verifies or creates an active connection via RUBE_MANAGE_CONNECTIONS and runs toolkit actions using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), always passing memory and a session_id. The flow emphasizes dynamic discovery, schema-driven arguments, and pagination-aware result collection.

When to use it

  • Automating case creation, updates, routing, or escalation workflows in Salesforce Service Cloud
  • Running bulk imports/exports or mass updates using Composio remote workbench
  • Embedding Salesforce Service Cloud actions inside multi-step agent workflows
  • Building integrations that must adapt to changing tool schemas or connection states
  • Executing repeatable operational tasks with strict schema validation and session control

Best practices

  • Always call RUBE_SEARCH_TOOLS first to get current tool slugs and input schemas; never hardcode them
  • Verify toolkit connection status with RUBE_MANAGE_CONNECTIONS and complete any returned auth steps until status is ACTIVE
  • Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls (use {} if nothing to persist)
  • Reuse session_id across related steps; generate a new session_id for distinct workflows
  • Respect schema types and exact field names from search results; handle pagination tokens until fully fetched

Example use cases

  • Create and assign incoming support cases: discover create-case tool, validate connection, then execute with schema-compliant fields
  • Bulk update contact records: use RUBE_SEARCH_TOOLS, then launch a RUBE_REMOTE_WORKBENCH run_composio_tool() job for high-volume changes
  • Automated escalation pipeline: combine multiple toolkit calls in a single session to check SLAs, update cases, and notify agents
  • Ad-hoc data retrieval: fetch case lists with pagination handling and transform results for reporting or downstream agents

FAQ

Do I need API keys to use Rube MCP?

No API keys are required; add https://rube.app/mcp as an MCP server in your client configuration to connect.

What if a tool schema changes?

Always call RUBE_SEARCH_TOOLS before executing. Update your argument structure to match the returned schema and types.