codeinterpreter-automation

通过 Rube MCP 自动执行 Code Interpreter 任务与数据处理流程

来源

GitHub

更新于

2026-06-07

// 安全评估低风险

仅提示词，不执行代码
开源可审计

正在进行安全审计…

凭证密钥
网络外发
代码执行
数据访问
来源供应链

// 安装

复制安装指令，让 AI 自动完成配置 · 推荐新手

请帮我安装 askskill 上的 "codeinterpreter-automation" 技能：
1. 下载 https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/codeinterpreter-automation/SKILL.md
2. 保存为 ~/.claude/skills/codeinterpreter-automation/SKILL.md
3. 装好后重载技能，告诉我可以用了

// 下载

下载 SKILL.md机读安装清单 ↗

// 用法示例

批量生成数据分析报告

输入

先搜索可用工具及其最新 schema，然后用 Rube MCP 自动触发 Code Interpreter：读取 sales.csv，完成数据清洗、月度趋势分析、异常值检测，并输出一份包含结论、图表说明和关键指标的中文报告。

预期产出

一份结构清晰的分析报告，包含清洗结果、趋势结论、异常说明与关键指标摘要。

自动运行并修复脚本

输入

先搜索工具 schema，再通过 Rube MCP 调用 Code Interpreter：执行我提供的 Python 脚本，定位报错原因，自动修改代码，并返回修复后的完整版本、修改说明和运行结果。

预期产出

返回可运行的修复后脚本，并附上错误原因、修改点和验证结果。

搭建定时自动化流程

输入

先搜索当前可用工具及 schema，然后设计一个基于 Rube MCP 的自动化流程：每天抓取指定 CSV 文件，交给 Code Interpreter 做汇总统计，生成结果文件，并说明每一步配置方式与触发逻辑。

预期产出

一套可落地的自动化方案，包含流程步骤、配置建议、触发机制和输出说明。

// 文档

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`