highlevel-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/highlevel-automation --openclawHighlevel Automation via Rube MCP
Automate Highlevel operations through Composio's Highlevel toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/highlevel
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Highlevel connection via
RUBE_MANAGE_CONNECTIONSwith toolkithighlevel - 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 toolkithighlevel - 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: "Highlevel 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 Highlevel task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["highlevel"]
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 Highlevel-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit highlevel |
| 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/highlevel-automation/SKILL.mdView on GitHub Overview
Automate Highlevel operations through Composio's Highlevel toolkit using Rube MCP. This skill emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before running any workflow to adapt to changes in tool slugs and input schemas. Proper setup ensures a schema-driven, reliable automation flow.
How This Skill Works
You connect Rube MCP and confirm RUBE_SEARCH_TOOLS is available, then manage the Highlevel connection with RUBE_MANAGE_CONNECTIONS. Next you discover tools, verify the connection is ACTIVE, and execute tools via RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug and its schema, along with a memory payload and a session_id to maintain context.
When to Use It
- Starting a new Highlevel automation by first discovering current tool schemas with RUBE_SEARCH_TOOLS.
- When tool schemas change and you need to refresh tool slugs and input requirements before execution.
- Coordinating a Highlevel workflow that requires ensuring the connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.
- Chaining multiple tools in a single session for a batch task using RUBE_MULTI_EXECUTE_TOOL and a memory payload.
- Performing bulk operations or onboarding sequences by reusing session IDs and executing multiple discovered tools.
Quick Start
- Step 1: Verify Rube MCP connection and that RUBE_SEARCH_TOOLS responds.
- Step 2: Run RUBE_SEARCH_TOOLS to fetch available Highlevel tool slugs and input schemas.
- Step 3: Ensure RUBE_MANAGE_CONNECTIONS shows ACTIVE, then run RUBE_MULTI_EXECUTE_TOOL with the discovered tool slug, including memory and session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing any Highlevel tools to get up-to-date schemas.
- Verify that RUBE_MANAGE_CONNECTIONS shows an ACTIVE status before running workflows.
- Use the exact field names and types from the search results; do not hardcode slugs or arguments.
- Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if it is empty, to maintain state.
- Reuse session IDs within a single workflow but generate new IDs for new workflows to avoid cross-context leakage.
Example Use Cases
- Create a new contact in Highlevel and attach them to a pipeline using a discovered tool slug and its input schema.
- Advance a deal to the next stage based on a lead score by executing the appropriate Highlevel tool from the current schemas.
- Batch-create tasks for a list of new leads in a single workflow using a discovered tool slug and memory state.
- Enroll multiple leads into a welcome nurture sequence by chaining tools in one session.
- Generate a daily activity report by executing multiple Highlevel tools in a single run with proper session handling.
