Do I always need to call RUBE_SEARCH_TOOLS before running tools?

Yes. It fetches current tool slugs, input schemas, and execution plans to avoid hardcoding.

Can I hardcode tool slugs or inputs?

No. Tool schemas change; rely on live results from RUBE_SEARCH_TOOLS.

What if the connection status is not ACTIVE?

Follow the returned auth link to complete setup, then retry until RUBE_MANAGE_CONNECTIONS shows ACTIVE.

anthropic-administrator-automation

Scanned

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

Files (1)

SKILL.md

3.0 KB

Anthropic Admin Automation via Rube MCP

Automate Anthropic Admin operations through Composio's Anthropic Admin toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/anthropic_administrator

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Anthropic Admin connection via RUBE_MANAGE_CONNECTIONS with toolkit anthropic_administrator
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 anthropic_administrator
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: "Anthropic Admin 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 Anthropic Admin task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["anthropic_administrator"]
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 Anthropic Admin-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `anthropic_administrator`
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/anthropic-administrator-automation/SKILL.md

View on GitHub

Overview

Automate Anthropic Admin operations through Composio's Anthropic Admin toolkit via Rube MCP. This skill streamlines setup, discovery, and execution of admin tools while guarding against schema drift by always querying current tool schemas.

How This Skill Works

Connect to Rube MCP and run RUBE_SEARCH_TOOLS to fetch available tools for the anthropic_administrator toolkit. Verify the connection with RUBE_MANAGE_CONNECTIONS, ensuring the status is ACTIVE. When ready, execute a tool using RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug and the exact input schema, always including memory in the call and reusing session IDs across the workflow.

When to Use It

Starting a new Anthropic Admin automation workflow and you need current tool slugs and schemas
Admin tool schemas change and you must fetch updated slugs and arguments before running tasks
Planning a sequence of admin operations via the core workflow pattern (discover, connect, execute)
Validating and maintaining an active Anthropic Admin connection prior to tool execution
Performing bulk admin tasks or orchestration via RUBE_REMOTE_WORKBENCH or multi-tool execution

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client and verify RUBE_SEARCH_TOOLS responds
Step 2: Run RUBE_MANAGE_CONNECTIONS with toolkits: ["anthropic_administrator"] and complete auth if needed
Step 3: Use RUBE_SEARCH_TOOLS to discover tools, then run RUBE_MULTI_EXECUTE_TOOL with the chosen tool_slug and memory: {} and the session_id from Step 2

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing any tool
Use exact field names and types from the search results; avoid hardcoding
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs within a workflow and handle pagination tokens when present

Example Use Cases

Discover available Anthropic Admin tools, connect, and automate onboarding a new admin user
Synchronize admin configurations across environments by applying discovered tool schemas
Audit admin settings and update policies using a guided multi-step tool execution plan
Execute bulk admin tasks via RUBE_REMOTE_WORKBENCH with run_composio_tool()
Handle paginated tool lists and reuse session IDs to maintain continuity

Frequently Asked Questions

Add this skill to your agents