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

agent tool_use skill risk: high

Endorsal Automation via Rube MCP

Instructs the model to automate Endorsal operations through Composio's Endorsal toolkit by first calling RUBE_SEARCH_TOOLS to discover current schemas, verifying ACTIVE status via…

  • Human review
  • External action: high

SKILL 1 file

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

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["endorsal"]
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 Endorsal-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `endorsal` |
| 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
  • Endorsal toolkit connection status

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL

ROLES & RULES

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

EXPECTED OUTPUT

Format
markdown
Schema
table · Operation, Approach
Constraints
  • include setup steps
  • always start with RUBE_SEARCH_TOOLS
  • use exact schemas from tool discovery

SUCCESS CRITERIA

  • Always search first for current tool schemas
  • Verify ACTIVE connection status before execution
  • Use exact schema-compliant arguments from search results
  • Include memory parameter on every RUBE_MULTI_EXECUTE_TOOL call
  • Reuse session IDs within a workflow

FAILURE MODES

  • Hardcoding tool slugs or arguments without first calling RUBE_SEARCH_TOOLS
  • Executing tools before confirming ACTIVE connection status
  • Omitting the memory parameter on RUBE_MULTI_EXECUTE_TOOL
  • Failing to handle pagination tokens

EXAMPLES

Includes multiple example RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL calls plus a quick-reference table.

CAVEATS

Dependencies
  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Endorsal connection via RUBE_MANAGE_CONNECTIONS
Missing context
  • Concrete examples of common Endorsal operations (e.g., create testimonial, list reviews).
  • Error-handling or retry guidance when tool calls fail.
  • Target client or environment (e.g., Claude Desktop, specific MCP host).
Ambiguities
  • Placeholders such as "your specific Endorsal task" and "TOOL_SLUG_FROM_SEARCH" are not replaced with concrete examples.
  • Session management instructions mix "generate_id: true" with reuse of "existing_session_id" without clear rules for when to generate vs. reuse.

QUALITY

OVERALL
0.79
CLARITY
0.85
SPECIFICITY
0.78
REUSABILITY
0.72
COMPLETENESS
0.80

IMPROVEMENT SUGGESTIONS

  • Add a short "Example: Retrieve all testimonials" section that shows the full sequence of calls with realistic arguments.
  • Replace generic placeholders with at least two fully-worked sample queries in the Tool Discovery and Core Workflow sections.
  • Explicitly state the expected shape of the `memory` object and whether it can be omitted when empty.

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