coupa-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/coupa-automation --openclawCoupa Automation via Rube MCP
Automate Coupa operations through Composio's Coupa toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/coupa
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Coupa connection via
RUBE_MANAGE_CONNECTIONSwith toolkitcoupa - 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 toolkitcoupa - 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: "Coupa 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 Coupa task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["coupa"]
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 Coupa-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit coupa |
| 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/coupa-automation/SKILL.mdView on GitHub Overview
Automate Coupa operations using Composio's Coupa toolkit through Rube MCP. This skill emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before executing workflows to adapt to changes.
How This Skill Works
Connect Rube MCP to Coupa, then fetch current tool schemas with RUBE_SEARCH_TOOLS. Validate the connection with RUBE_MANAGE_CONNECTIONS and execute the discovered tools using RUBE_MULTI_EXECUTE_TOOL with the appropriate tool_slug and arguments, including memory payloads. Always use the latest schemas to ensure compatibility.
When to Use It
- Automating routine Coupa operations like PO creation, invoice processing, or vendor data updates using dynamically discovered tool slugs.
- When tool schemas change frequently and you must fetch current definitions before automation.
- When you need to verify that the Coupa connection is ACTIVE before running workflows.
- When you want to reuse a session ID across multiple steps within a single workflow.
- For bulk or chained Coupa actions using RUBE_REMOTE_WORKBENCH or multiple tool executions.
Quick Start
- Step 1: Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed.
- Step 2: Discover tools: Run RUBE_SEARCH_TOOLS with a Coupa use_case to retrieve current tool slugs and schemas.
- Step 3: Execute: Use RUBE_MULTI_EXECUTE_TOOL with the chosen tool_slug, proper arguments from the schema, memory, and a session_id; verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to get current tool schemas and avoid hardcoding slugs.
- Check that RUBE_MANAGE_CONNECTIONS indicates an ACTIVE status before executing tools.
- Use exact field names and types from the search results to build tool arguments.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and handle pagination if tool results are paginated.
Example Use Cases
- Discover Coupa operations with RUBE_SEARCH_TOOLS and run a PO creation tool using the returned slug and required arguments.
- Validate vendor data against Coupa and update vendor records via the corresponding automation tool discovered at runtime.
- Update multiple line items by discovering the appropriate tool slug and executing it with the required schema-compliant arguments.
- Ensure the Coupa connection is ACTIVE with RUBE_MANAGE_CONNECTIONS before performing a batch of tasks.
- Paginate through tool schemas using RUBE_GET_TOOL_SCHEMAS or RUBE_SEARCH_TOOLS and iterate over multiple tool executions.