What is Rube MCP and why do I need it?

Rube MCP is Composio's MCP server that lets you discover and manage tool schemas and execute tools programmatically; always connect and confirm tool schemas before running.

Do I need to search tools every time?

Yes; tool schemas can change, so rely on RUBE_SEARCH_TOOLS first to avoid hardcoding.

What should I include in memory?

Include memory even if empty, as required by RUBE_MULTI_EXECUTE_TOOL calls.

gladia-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/gladia-automation --openclaw

Files (1)

SKILL.md

2.8 KB

Gladia Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/gladia

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Gladia connection via RUBE_MANAGE_CONNECTIONS with toolkit gladia
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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit gladia
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: "Gladia 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 Gladia task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["gladia"]
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 Gladia-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `gladia`
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/gladia-automation/SKILL.mdView on GitHub

Overview

Automate Gladia operations through Composio's Gladia toolkit via Rube MCP. Always search for current tool schemas before execution and ensure an ACTIVE Gladia connection for reliable workflows.

How This Skill Works

Connect to Gladia via Rube MCP and verify an ACTIVE connection using RUBE_MANAGE_CONNECTIONS. Discover available Gladia tools with RUBE_SEARCH_TOOLS to fetch slugs and input schemas, then execute them with RUBE_MULTI_EXECUTE_TOOL, including a memory object. This approach keeps tool definitions current and avoids hardcoding tool details.

When to Use It

You need to automate a sequence of Gladia tasks and want up-to-date tool schemas.
You're validating a Gladia workflow and must confirm the connection status is ACTIVE before execution.
You're iterating on a workflow and want to fetch fresh tool schemas instead of using static slugs.
You want to reuse a session ID across related steps in a single workflow.
You're performing bulk or chained tool executions with RUBE_MULTI_EXECUTE_TOOL in a compliant manner.

Quick Start

Step 1: Add Rube MCP endpoint https://rube.app/mcp as an MCP server in your client config.
Step 2: Run RUBE_SEARCH_TOOLS to fetch current Gladia tool slugs and input schemas.
Step 3: Run RUBE_MANAGE_CONNECTIONS with toolkit 'gladia' and, if ACTIVE, execute tools with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and memory.

Best Practices

Always run RUBE_SEARCH_TOOLS before selecting tools.
Check RUBE_MANAGE_CONNECTIONS status is ACTIVE before executing tools.
Use exact field names/types from the tool schemas.
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls (even if empty).
Reuse session IDs for related workflows; avoid creating new sessions for the same run.

Example Use Cases

Discover Gladia tools, choose a workflow, and run a tool via RUBE_MULTI_EXECUTE_TOOL.
Establish a Gladia connection and perform a data retrieval task using a discovered tool.
Iterate on a Gladia pipeline by fetching updated tool schemas and re-running with new inputs.
Run multiple tools in sequence using a single session.
Bulk-operate Gladia tasks with RUBE_REMOTE_WORKBENCH run_composio_tool for batch processing.

Frequently Asked Questions

Add this skill to your agents