What is grafbase-automation?

A method to automate Grafbase operations via the Rube MCP framework within Composio, using up-to-date tool schemas.

Do I always need to search tools first?

Yes. The workflow requires RUBE_SEARCH_TOOLS to fetch current tool slugs and input schemas before any execution.

What should I include in the memory parameter?

Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty, to maintain state across tool executions.

grafbase-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/grafbase-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Grafbase Automation via Rube MCP

Automate Grafbase operations through Composio's Grafbase toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/grafbase

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Grafbase connection via RUBE_MANAGE_CONNECTIONS with toolkit grafbase
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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit grafbase
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: "Grafbase 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 Grafbase task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["grafbase"]
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 Grafbase-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `grafbase`
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/grafbase-automation/SKILL.mdView on GitHub

Overview

Grafbase Automation via Rube MCP enables executing Grafbase tasks through Composio's Grafbase toolkit. It relies on discovering current tool schemas with RUBE_SEARCH_TOOLS before running workflows to ensure accuracy. This approach reduces errors and speeds up Grafbase tasks through structured, schema-driven automation.

How This Skill Works

First, you call RUBE_SEARCH_TOOLS to discover available Grafbase tools and their input schemas. Then you verify and activate the Grafbase connection with RUBE_MANAGE_CONNECTIONS. Finally, you execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL using the tool_slug and schema-compliant arguments, always including memory and a session_id.

When to Use It

When starting a Grafbase workflow and you need the most up-to-date tool schemas before execution.
When you need to validate and establish an ACTIVE Grafbase connection via RUBE_MANAGE_CONNECTIONS.
When you want to discover available Grafbase tools and their required inputs before running a task.
When you are ready to run a Grafbase operation using a discovered tool slug and proper arguments.
When performing bulk Grafbase operations or handling multiple tools in sequence (RUBE_REMOTE_WORKBENCH).

Quick Start

Step 1: Verify RUBE MCP is connected and RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: [grafbase] to activate Grafbase.
Step 3: Use RUBE_MULTI_EXECUTE_TOOL with a discovered tool_slug and memory: {} to run the task.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
Ensure the Grafbase connection shows ACTIVE in RUBE_MANAGE_CONNECTIONS before execution.
Use exact field names and types from the discovered tool schemas; avoid hardcoding.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
Reuse session IDs within a workflow and paginate responses as needed to complete results.

Example Use Cases

Discover Grafbase tools with RUBE_SEARCH_TOOLS, then execute a chosen tool slug to deploy a schema.
Connect to Grafbase via RUBE_MANAGE_CONNECTIONS and verify ACTIVE before running a workflow.
Run a Grafbase operation using RUBE_MULTI_EXECUTE_TOOL with the proper input schema from search results.
Bulk-run several Grafbase tasks using RUBE_REMOTE_WORKBENCH after discovering tools.
Retrieve full tool schemas with RUBE_GET_TOOL_SCHEMAS to validate exact field requirements.

Frequently Asked Questions

Add this skill to your agents