What is RUBE MCP and how does it relate to Codeinterpreter automation?

RUBE MCP is Composio's management plane for toolkits. You use it to search for tool schemas, manage connections, and execute tools in a structured workflow for Codeinterpreter automation.

Do I always need to call RUBE_SEARCH_TOOLS before running a workflow?

Yes. Tool schemas can change, so always search for current tool slugs and input schemas before execution to ensure compatibility.

What should I include in memory for RUBE_MULTI_EXECUTE_TOOL?

Include the memory parameter in every RUBE_MULTI_EXECUTE_TOOL call, even if empty, to preserve context across steps.

codeinterpreter-automation

Scanned

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

Files (1)

SKILL.md

3.0 KB

Codeinterpreter Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/codeinterpreter

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["codeinterpreter"]
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 Codeinterpreter-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `codeinterpreter`
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/codeinterpreter-automation/SKILL.md

View on GitHub

Overview

Automate Codeinterpreter operations through Composio's Rube MCP toolkit. It emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before execution, and managing the Codeinterpreter connection with RUBE_MANAGE_CONNECTIONS. This approach keeps workflows resilient to schema changes and ensures correct argument formats.

How This Skill Works

The workflow starts by discovering available tools with RUBE_SEARCH_TOOLS, then verifies an ACTIVE connection via RUBE_MANAGE_CONNECTIONS, and finally executes tools with RUBE_MULTI_EXECUTE_TOOL using memory and a session_id. Always use the exact fields from the discovered schema and pass in memory even if empty.

When to Use It

Orchestrate end-to-end Codeinterpreter tasks by discovering tools, selecting a tool, and executing with proper arguments.
When tool schemas change, re-search schemas before calling tools to avoid broken workflows.
Run session-based workflows that require memory preservation across steps using RUBE_MULTI_EXECUTE_TOOL.
Coordinate multi-tool executions or bulk operations via RUBE_MULTI_EXECUTE_TOOL and related bulk interfaces.
Ensure the Codeinterpreter connection is ACTIVE before any tool execution.

Quick Start

Step 1: Verify RUBE MCP is connected and run RUBE_SEARCH_TOOLS to discover current codeinterpreter tools.
Step 2: Use RUBE_MANAGE_CONNECTIONS to ensure toolkit codeinterpreter is ACTIVE.
Step 3: Execute a tool with RUBE_MULTI_EXECUTE_TOOL, including memory: {} and the current session_id.

Best Practices

Always search first to retrieve current tool schemas.
Verify connection is ACTIVE before execution.
Use exact field names/types from the search results.
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls.
Reuse session IDs within a workflow and refresh for new flows.

Example Use Cases

Automate a data analysis sequence by discovering Codeinterpreter tools, selecting a data-cleaning tool, then a model evaluation tool, all in a single session.
After a schema update, re-run RUBE_SEARCH_TOOLS to refresh tool slugs and adjust your workflow accordingly.
Execute multiple tools in one go using RUBE_MULTI_EXECUTE_TOOL with memory preserved between steps.
Before starting a workflow, verify RUBE_MANAGE_CONNECTIONS reports ACTIVE to prevent failed runs.
Reuse the same session_id across related tasks to maintain context and memory continuity.

Frequently Asked Questions

Add this skill to your agents