griptape-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/griptape-automation --openclawGriptape Automation via Rube MCP
Automate Griptape operations through Composio's Griptape toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/griptape
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Griptape connection via
RUBE_MANAGE_CONNECTIONSwith toolkitgriptape - 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 toolkitgriptape - 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: "Griptape 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 Griptape task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["griptape"]
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 Griptape-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit griptape |
| 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/griptape-automation/SKILL.mdView on GitHub Overview
Automate Griptape operations using Composio's Griptape toolkit through the Rube MCP platform. This skill enforces discovering current tool schemas first and requires an active Griptape connection and RUBE_SEARCH_TOOLS readiness. It reduces manual steps and helps keep tool references up-to-date.
How This Skill Works
Begin by calling RUBE_SEARCH_TOOLS to list available Griptape tools and their input schemas. Then verify the Griptape connection is ACTIVE with RUBE_MANAGE_CONNECTIONS, and finally execute the desired tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and schema-compliant arguments. Always include memory and reuse sessions for related tasks to maintain state.
When to Use It
- When you need to automate a specific Griptape operation after fetching current tool schemas.
- When re-running a workflow with updated tool schemas without hardcoding slugs.
- When batching multiple Griptape tasks, using RUBE_MULTI_EXECUTE_TOOL in a single session.
- When validating the Griptape connection status before execution.
- When troubleshooting schema changes by re-discovering tools and updating inputs.
Quick Start
- Step 1: Ensure Rube MCP is configured and RUBE_SEARCH_TOOLS responds.
- Step 2: Use RUBE_MANAGE_CONNECTIONS with toolkit griptape to activate the connection.
- Step 3: Run RUBE_MULTI_EXECUTE_TOOL with a discovered tool slug and memory field.
Best Practices
- Always run RUBE_SEARCH_TOOLS first to fetch current tool schemas.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing.
- Use exact field names and types from the tool discovery response.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL, even if empty.
- Reuse session IDs for related tasks to enable flow continuity.
Example Use Cases
- Discover tools for a Griptape task, then execute TOOL_SLUG_FROM_SEARCH with matching arguments.
- Test a schema update by re-discovering tools and re-running a workflow in the same session.
- Batch-run several Griptape tools with RUBE_MULTI_EXECUTE_TOOL and shared memory.
- Re-establish a dropped Griptape connection by running RUBE_MANAGE_CONNECTIONS and retry.
- Debug a failing tool by re-fetching schemas and confirming input field names before retry.