crustdata-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/crustdata-automation --openclawCrustdata Automation via Rube MCP
Automate Crustdata operations through Composio's Crustdata toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/crustdata
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Crustdata connection via
RUBE_MANAGE_CONNECTIONSwith toolkitcrustdata - 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 toolkitcrustdata - 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: "Crustdata 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 Crustdata task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["crustdata"]
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 Crustdata-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit crustdata |
| 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/crustdata-automation/SKILL.mdView on GitHub Overview
This skill automates Crustdata operations through Composio's Crustdata toolkit using Rube MCP. It emphasizes discovering current tool schemas before execution and validating active connections to prevent failures. By orchestrating discovery, connection checks, and tool execution, it streamlines repetitive Crustdata tasks.
How This Skill Works
It begins by calling RUBE_SEARCH_TOOLS to fetch available Crustdata tools and their input schemas. It then uses RUBE_MANAGE_CONNECTIONS to ensure an ACTIVE Crustdata connection, and finally executes the chosen tool via RUBE_MULTI_EXECUTE_TOOL, supplying a memory payload and a session_id. Always rely on the live tool schemas returned by search to drive arguments rather than hardcoding slugs.
When to Use It
- Automate Crustdata operations end-to-end using current tool schemas fetched with RUBE_SEARCH_TOOLS.
- When you must confirm and maintain an ACTIVE Crustdata connection before running workflows.
- When starting a Crustdata task by discovering available tools and recommended execution plans.
- For bulk Crustdata tasks, execute multiple tools efficiently with RUBE_REMOTE_WORKBENCH run_composio_tool.
- When handling dynamic schemas or paginated tool listings, refresh tool definitions before proceeding.
Quick Start
- Step 1: Add the Rube MCP endpoint (https://rube.app/mcp) and confirm RUBE_SEARCH_TOOLS is responsive.
- Step 2: Run RUBE_SEARCH_TOOLS for a Crustdata use_case to list tools and input schemas.
- Step 3: Manage connection to crustdata and execute a tool with RUBE_MULTI_EXECUTE_TOOL using memory and session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas and avoid hardcoding slugs.
- Verify RUBE_MANAGE_CONNECTIONS reports ACTIVE before any tool execution.
- Use exact field names and types from the search results; mirror the discovered input schemas.
- Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
- Reuse session IDs within a workflow and generate new IDs for new tasks; watch for pagination tokens.
Example Use Cases
- 1) Discover Crustdata tools with RUBE_SEARCH_TOOLS, pick a task, and execute it via RUBE_MULTI_EXECUTE_TOOL with proper args.
- 2) Establish a crustdata connection using RUBE_MANAGE_CONNECTIONS and only run tools when ACTIVE.
- 3) Run multiple Crustdata tasks in bulk using RUBE_REMOTE_WORKBENCH's run_composio_tool for throughput.
- 4) Regularly verify tool schemas with RUBE_GET_TOOL_SCHEMAS to avoid drift from live definitions.
- 5) Build repeatable Crustdata automation that reuses a session_id across steps and includes memory payloads.
