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

agent tool_use skill risk: medium

Botstar Automation via Rube MCP

Provides instructions for automating Botstar operations through Composio's Botstar toolkit via Rube MCP, including prerequisites, setup steps, tool discovery with RUBE_SEARCH_TOOLS…

  • External action: medium

SKILL 1 file

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

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

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

## Prerequisites

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

### Step 2: Check Connection

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

INPUTS

use_case REQUIRED

Botstar task description for tool search

e.g. Botstar operations

session_id

Session identifier for workflow continuity

tool_slug REQUIRED

Tool identifier returned from search

REQUIRED CONTEXT

  • Rube MCP connection
  • Botstar toolkit connection via RUBE_MANAGE_CONNECTIONS

OPTIONAL CONTEXT

  • specific Botstar use case
  • existing session_id

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_GET_TOOL_SCHEMAS
  • RUBE_REMOTE_WORKBENCH

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. Call RUBE_MANAGE_CONNECTIONS with toolkit botstar
  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
  • include memory parameter

SUCCESS CRITERIA

  • Verify Rube MCP is available
  • Confirm connection status shows ACTIVE
  • Discover tools before execution
  • Follow core workflow pattern in order

FAILURE MODES

  • May hardcode tool slugs without searching first
  • May skip connection status verification
  • May omit memory parameter in execute calls
  • May fail to reuse session IDs

CAVEATS

Dependencies
  • Requires Rube MCP connected
  • Requires active Botstar connection via RUBE_MANAGE_CONNECTIONS
  • Requires RUBE_SEARCH_TOOLS available
Missing context
  • Target MCP client or environment where the prompt will be used
  • Expected output format for workflow results
Ambiguities
  • Placeholder text 'your specific Botstar task' left in example without explicit instruction on substitution.

QUALITY

OVERALL
0.80
CLARITY
0.82
SPECIFICITY
0.88
REUSABILITY
0.71
COMPLETENESS
0.79

IMPROVEMENT SUGGESTIONS

  • Replace inline code blocks with explicit {{placeholder}} syntax for session_id, use_case, and tool_slug to improve templating.
  • Add a one-sentence success criterion at the end (e.g., 'Workflow succeeds when all tool calls return status 200 and connection remains ACTIVE').

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