keap-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/keap-automation --openclawKeap Automation via Rube MCP
Automate Keap operations through Composio's Keap toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/keap
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Keap connection via
RUBE_MANAGE_CONNECTIONSwith toolkitkeap - 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 toolkitkeap - 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: "Keap 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 Keap task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["keap"]
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 Keap-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit keap |
| 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/keap-automation/SKILL.mdView on GitHub Overview
Keap Automation via Rube MCP enables automating Keap operations using Composio's Keap toolkit. It emphasizes discovering current tool schemas first, establishing an ACTIVE Keap connection, and executing tools with memory for reliable workflows.
How This Skill Works
This skill uses Rube MCP to discover available Keap tools, verify an ACTIVE connection to Keap, and then execute chosen tools with schema-compliant arguments. Always call RUBE_SEARCH_TOOLS to obtain up-to-date tool slugs and input schemas, then use RUBE_MANAGE_CONNECTIONS to confirm the toolkit and finally run tools via RUBE_MULTI_EXECUTE_TOOL, including a memory payload.
When to Use It
- You need to automate a Keap operation and want up-to-date tool schemas before execution.
- You must verify that the Keap connection is ACTIVE before running any workflows.
- You intend to run one or more Keap tool actions in a single session with reusing session IDs.
- You are performing bulk or chained Keap tasks using supported pipelines or bulk ops.
- You want to handle potential pagination in tool discovery responses and avoid hardcoding tool slugs.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server and verify RUBE_SEARCH_TOOLS responds.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit 'keap' and ensure the status is ACTIVE.
- Step 3: Discover tools with RUBE_SEARCH_TOOLS, then execute a chosen tool via RUBE_MULTI_EXECUTE_TOOL using the memory payload.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to get current tool schemas before any run.
- Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
- Use exact field names and types from the search results; avoid hardcoded slugs.
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
- Reuse session IDs within a workflow and manage pagination tokens when discovering tools.
Example Use Cases
- Discover a Keap tool to create a new contact and execute it using the returned slug and input schema.
- Update a Keap record by first fetching the correct tool slug from RUBE_SEARCH_TOOLS, then executing with exact fields.
- Connect to Keap via RUBE_MANAGE_CONNECTIONS and run a sequence of tools in a single session.
- Perform bulk Keap operations using RUBE_REMOTE_WORKBENCH with run_composio_tool for efficiency.
- Handle tool discovery pagination to fetch all available Keap tools without hardcoding slugs.
