Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Agencyzoom Automation via Rube MCP

agent operations skill risk: medium

Agencyzoom Automation via Rube MCP

The prompt provides step-by-step instructions for automating Agencyzoom operations through Composio's toolkit using Rube MCP tools such as RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTION…

  • Human review
  • External action: high

SKILL 1 file

SKILL.md
---
name: agencyzoom-automation
description: "Automate Agencyzoom tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# Agencyzoom Automation via Rube MCP

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

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Agencyzoom connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `agencyzoom`
- 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 `agencyzoom`
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: "Agencyzoom 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 Agencyzoom task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["agencyzoom"]
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 Agencyzoom-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `agencyzoom` |
| 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)*

REQUIRED CONTEXT

  • Rube MCP connection status
  • Agencyzoom connection via RUBE_MANAGE_CONNECTIONS

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_REMOTE_WORKBENCH
  • RUBE_GET_TOOL_SCHEMAS

ROLES & RULES

  1. Always search tools first for current schemas
  2. Always call RUBE_SEARCH_TOOLS first to get current tool schemas
  3. Always discover available tools before executing workflows
  4. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  5. Confirm connection status shows ACTIVE before running any workflows
  6. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
  7. Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
  8. Use exact field names and types from the search results
  9. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
  10. Reuse session IDs within a workflow
  11. Generate new session IDs for new workflows
  12. Check responses for pagination tokens and continue fetching until complete

EXPECTED OUTPUT

Format
markdown
Constraints
  • include prerequisites, setup steps, tool discovery pattern, core workflow, known pitfalls, and quick reference table

SUCCESS CRITERIA

  • Always search first
  • Check connection is ACTIVE
  • Use schema-compliant arguments
  • Include memory parameter
  • Reuse sessions correctly

FAILURE MODES

  • Hardcoding tool slugs without searching first
  • Executing tools before confirming ACTIVE connection
  • Using incorrect field names or types
  • Omitting the memory parameter
  • Not reusing session IDs

EXAMPLES

Includes multiple example RUBE tool calls (SEARCH_TOOLS, MANAGE_CONNECTIONS, MULTI_EXECUTE_TOOL) with sample arguments and session handling.

CAVEATS

Dependencies
  • Rube MCP connection (RUBE_SEARCH_TOOLS available)
  • Active Agencyzoom connection via RUBE_MANAGE_CONNECTIONS
Missing context
  • Concrete examples of successful tool calls with real schemas
  • Error handling or retry logic for failed executions
Ambiguities
  • The exact syntax/format for calling RUBE_* functions is shown inconsistently (markdown code blocks vs. parameter lists).
  • session: {generate_id: true} syntax is not explained or standardized.

QUALITY

OVERALL
0.74
CLARITY
0.78
SPECIFICITY
0.72
REUSABILITY
0.68
COMPLETENESS
0.81

IMPROVEMENT SUGGESTIONS

  • Replace placeholder strings like "your specific Agencyzoom task" with 2-3 concrete example queries.
  • Define a consistent, copy-pasteable JSON or function-call format for all RUBE_* invocations.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT