sage-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/sage-automation --openclawSage Automation via Rube MCP
Automate Sage operations through Composio's Sage toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/sage
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Sage connection via
RUBE_MANAGE_CONNECTIONSwith toolkitsage - 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 toolkitsage - 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: "Sage 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 Sage task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["sage"]
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 Sage-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit sage |
| 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/sage-automation/SKILL.mdView on GitHub Overview
Automate Sage operations through Composio's Sage toolkit using Rube MCP. This approach emphasizes discovering current tool schemas before execution and requires an active Sage connection. Follow the setup steps to connect, validate tools, and run workflows safely.
How This Skill Works
Tools are discovered with RUBE_SEARCH_TOOLS to obtain tool slugs and input schemas. You then verify the Sage connection with RUBE_MANAGE_CONNECTIONS and ensure it's ACTIVE. Finally, execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL, including memory and the current session_id.
When to Use It
- When you need to automate a repeatable Sage task and want up-to-date tool schemas.
- When starting a Sage workflow, first discovering available tools via RUBE_SEARCH_TOOLS.
- When ensuring a Sage connection is ready (ACTIVE) before execution.
- When executing sequential Sage tools within a single session (reuse session_id).
- When performing bulk Sage operations or multiple tool runs with RUBE_REMOTE_WORKBENCH.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
- Step 2: Run RUBE_SEARCH_TOOLS to discover available Sage tools and their input schemas.
- Step 3: Run RUBE_MANAGE_CONNECTIONS with toolkit 'sage' and ensure ACTIVE, then execute tools with RUBE_MULTI_EXECUTE_TOOL using a valid session_id and memory.
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing tools to get current schemas.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before running tools.
- Use exact field names and types from search results; avoid hardcoding slugs.
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
- Reuse session IDs within a workflow and fetch new ones for new workflows.
Example Use Cases
- Automate a recurring Sage data export by discovering the right tool and running it with proper arguments.
- Validate the Sage connection, then run a specific Sage computation tool after tool discovery.
- Chain two Sage tools in a single session to generate a consolidated report.
- Perform bulk Sage operations using RUBE_REMOTE_WORKBENCH to run multiple tools in one batch.
- Inspect tool schemas via RUBE_GET_TOOL_SCHEMAS to prepare for a new Sage task.