home / skills / composiohq / awesome-claude-skills / cloudflare-automation

cloudflare-automation skill

safe

/cloudflare-automation

This skill automates Cloudflare operations through Composio's MCP toolkit, always discovering tool schemas and managing connections for reliable workflows.

npx playbooks add skill composiohq/awesome-claude-skills --skill cloudflare-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: cloudflare-automation
description: "Automate Cloudflare tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Cloudflare Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/cloudflare](https://composio.dev/toolkits/cloudflare)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Cloudflare connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudflare`
- 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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudflare`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Cloudflare 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 Cloudflare task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["cloudflare"]
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 Cloudflare-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudflare` |
| 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](https://composio.dev)*

Overview

This skill automates Cloudflare tasks through Composio's Cloudflare toolkit using Rube MCP. It provides a reliable workflow pattern to discover tools, validate connections, and execute Cloudflare operations programmatically. The skill emphasizes always searching tools first to read current schemas and avoid breaking changes.

How this skill works

It first calls RUBE_SEARCH_TOOLS to discover available tool slugs, input schemas, and recommended execution plans. Next it verifies an active Cloudflare connection via RUBE_MANAGE_CONNECTIONS, then runs actions using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk work). All calls use session IDs and include a memory parameter as required.

When to use it

Automate DNS, firewall, or page-rule changes across accounts
Run bulk updates or scripted maintenance in Cloudflare
Integrate Cloudflare operations into agent-driven workflows
Ensure safe execution when tool schemas may change frequently
Orchestrate multi-step Cloudflare tasks across sessions

Best practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas; never hardcode tool names or fields
Check RUBE_MANAGE_CONNECTIONS and confirm status is ACTIVE before executing tools
Pass the memory parameter (even if empty) to RUBE_MULTI_EXECUTE_TOOL calls
Reuse session_id for related steps; generate a new session for separate workflows
Handle pagination and follow pagination tokens until responses are complete
Validate arguments strictly against the discovered schema types and required fields

Example use cases

Discover and run a tool to create or update DNS records across zones
Check and renew Cloudflare API connections, then run bulk firewall rule changes
Automate certificate provisioning or SSL settings updates via discovered tools
Run scheduled maintenance: search tools, confirm connection, then execute a multi-step run to apply configuration changes
Use RUBE_REMOTE_WORKBENCH to run composio tools for high-volume or batched Cloudflare operations

FAQ

Why must I call RUBE_SEARCH_TOOLS every time?

Tool schemas and slugs can change; searching first ensures you use current input fields, types, and recommended execution plans to avoid errors.

What if RUBE_MANAGE_CONNECTIONS shows NOT_ACTIVE?

Follow the returned auth link or connection instructions from the manage connections response to complete authentication, then re-check until status is ACTIVE.