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

agent tool_use skill risk: medium

Docupilot Rube MCP Automation Guide

Instructs on automating Docupilot operations through Composio's toolkit via Rube MCP, covering prerequisites, setup steps, tool discovery with RUBE_SEARCH_TOOLS, connection managem…

  • Policy sensitive
  • Human review
  • External action: high

SKILL 1 file

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

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["docupilot"]
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 Docupilot-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `docupilot` |
| 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
  • active Docupilot 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. If connection is not ACTIVE, follow the returned auth link to complete setup
  6. Confirm connection status shows ACTIVE before running any workflows
  7. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
  8. Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
  9. Use exact field names and types from the search results
  10. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
  11. Reuse session IDs within a workflow
  12. Generate new session IDs for new workflows
  13. Check responses for pagination tokens and continue fetching until complete

EXPECTED OUTPUT

Format
markdown
Constraints
  • always call RUBE_SEARCH_TOOLS first
  • verify ACTIVE connection before execution
  • reuse session IDs within workflows

SUCCESS CRITERIA

  • Always search first
  • Check connection status is ACTIVE
  • Use schema-compliant arguments from search results
  • Include memory parameter in execute calls
  • Reuse session IDs within workflows

FAILURE MODES

  • Hardcoding tool slugs or arguments without searching first
  • Skipping connection verification before execution
  • Using incorrect field names or types
  • Omitting the memory parameter in MULTI_EXECUTE_TOOL
  • Failing to handle pagination

EXAMPLES

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

CAVEATS

Dependencies
  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Docupilot connection via RUBE_MANAGE_CONNECTIONS
  • Session ID from prior RUBE_SEARCH_TOOLS call
Missing context
  • Concrete task examples with expected outputs
  • Error handling or retry logic details

QUALITY

OVERALL
0.79
CLARITY
0.88
SPECIFICITY
0.82
REUSABILITY
0.68
COMPLETENESS
0.78

IMPROVEMENT SUGGESTIONS

  • Replace inline code blocks with explicit {{placeholder}} syntax for task-specific use cases to improve reusability.
  • Add a required 'output_format' parameter or section to standardize workflow results.

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