many_chat-automation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ManyChat Automation via Rube MCP

通过Rube MCP实现ManyChat自动化

Automate ManyChat operations through Composio's ManyChat toolkit via Rube MCP.
通过Composio的ManyChat工具包,借助Rube MCP自动化ManyChat的各项操作。

Prerequisites

前置条件

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active ManyChat connection via
    RUBE_MANAGE_CONNECTIONS
    with toolkit
    many_chat
  • Always call
    RUBE_SEARCH_TOOLS
    first to get current tool schemas
  • 必须已连接Rube MCP(需确保
    RUBE_SEARCH_TOOLS
    可用)
  • 通过
    RUBE_MANAGE_CONNECTIONS
    完成ManyChat的激活连接,工具包选择
    many_chat
  • 请始终先调用
    RUBE_SEARCH_TOOLS
    以获取最新的工具架构

Setup

设置步骤

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
    many_chat
  3. If connection is not ACTIVE, follow the returned auth link to complete setup
  4. Confirm connection status shows ACTIVE before running any workflows
获取Rube MCP:在客户端配置中添加
https://rube.app/mcp
作为MCP服务器。无需API密钥——只需添加该端点即可使用。
  1. 通过确认
    RUBE_SEARCH_TOOLS
    能正常响应,验证Rube MCP是否可用
  2. 调用
    RUBE_MANAGE_CONNECTIONS
    并指定工具包为
    many_chat
  3. 如果连接状态未显示为ACTIVE,请按照返回的授权链接完成设置
  4. 在运行任何工作流之前,确认连接状态已显示为ACTIVE

Tool Discovery

工具发现

Always discover available tools before executing workflows:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "chatbot flows, subscribers, broadcasts, and messenger automation", "known_fields": ""}]
This returns:
  • Available tool slugs for ManyChat
  • Recommended execution plan steps
  • Known pitfalls and edge cases
  • Input schemas for each tool
在执行工作流之前,请务必先发现可用工具:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "chatbot flows, subscribers, broadcasts, and messenger automation", "known_fields": ""}]
该调用会返回:
  • ManyChat的可用工具标识(slug)
  • 推荐的执行计划步骤
  • 已知的陷阱和边缘情况
  • 每个工具的输入架构

Core Workflows

核心工作流

1. Discover Available ManyChat Tools

1. 发现可用的ManyChat工具

RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available ManyChat tools and capabilities"
Review the returned tools, their descriptions, and input schemas before proceeding.
RUBE_SEARCH_TOOLS:
  queries:
    - use_case: "list all available ManyChat tools and capabilities"
在继续操作前,请查看返回的工具、工具描述以及输入架构。

2. Execute ManyChat Operations

2. 执行ManyChat操作

After discovering tools, execute them via:
RUBE_MULTI_EXECUTE_TOOL:
  tools:
    - tool_slug: "<discovered_tool_slug>"
      arguments: {<schema-compliant arguments>}
  memory: {}
  sync_response_to_workbench: false
发现工具后,通过以下方式执行:
RUBE_MULTI_EXECUTE_TOOL:
  tools:
    - tool_slug: "<discovered_tool_slug>"
      arguments: {<schema-compliant arguments>}
  memory: {}
  sync_response_to_workbench: false

3. Multi-Step Workflows

3. 多步骤工作流

For complex workflows involving multiple ManyChat operations:
  1. Search for all relevant tools:
    RUBE_SEARCH_TOOLS
    with specific use case
  2. Execute prerequisite steps first (e.g., fetch before update)
  3. Pass data between steps using tool responses
  4. Use
    RUBE_REMOTE_WORKBENCH
    for bulk operations or data processing
对于涉及多个ManyChat操作的复杂工作流:
  1. 使用特定的用例调用
    RUBE_SEARCH_TOOLS
    ,搜索所有相关工具
  2. 先执行前置步骤(例如,先获取数据再进行更新)
  3. 利用工具的返回结果在步骤之间传递数据
  4. 使用
    RUBE_REMOTE_WORKBENCH
    进行批量操作或数据处理

Common Patterns

常见模式

Search Before Action

操作前先搜索

Always search for existing resources before creating new ones to avoid duplicates.
在创建新资源之前,请务必先搜索现有资源,以避免重复。

Pagination

分页处理

Many list operations support pagination. Check responses for
next_cursor
or
page_token
and continue fetching until exhausted.
许多列表操作支持分页。请检查返回结果中的
next_cursor
page_token
,并持续获取数据直到全部加载完成。

Error Handling

错误处理

  • Check tool responses for errors before proceeding
  • If a tool fails, verify the connection is still ACTIVE
  • Re-authenticate via
    RUBE_MANAGE_CONNECTIONS
    if connection expired
  • 在继续操作前,请检查工具的返回结果是否存在错误
  • 如果工具执行失败,请验证ManyChat连接是否仍处于ACTIVE状态
  • 如果OAuth令牌过期,请通过
    RUBE_MANAGE_CONNECTIONS
    重新进行身份验证

Batch Operations

批量操作

For bulk operations, use
RUBE_REMOTE_WORKBENCH
with
run_composio_tool()
in a loop with
ThreadPoolExecutor
for parallel execution.
对于批量操作,请使用
RUBE_REMOTE_WORKBENCH
,结合
ThreadPoolExecutor
在循环中调用
run_composio_tool()
以实现并行执行。

Known Pitfalls

已知陷阱

  • Always search tools first: Tool schemas and available operations may change. Never hardcode tool slugs without first discovering them via
    RUBE_SEARCH_TOOLS
    .
  • Check connection status: Ensure the ManyChat connection is ACTIVE before executing any tools. Expired OAuth tokens require re-authentication.
  • Respect rate limits: If you receive rate limit errors, reduce request frequency and implement backoff.
  • Validate schemas: Always pass strictly schema-compliant arguments. Use
    RUBE_GET_TOOL_SCHEMAS
    to load full input schemas when
    schemaRef
    is returned instead of
    input_schema
    .
  • 始终先搜索工具:工具架构和可用操作可能会发生变化。切勿在未通过
    RUBE_SEARCH_TOOLS
    发现工具的情况下硬编码工具标识(slug)。
  • 检查连接状态:在执行任何工具之前,请确保ManyChat连接处于ACTIVE状态。过期的OAuth令牌需要重新进行身份验证。
  • 遵守速率限制:如果收到速率限制错误,请降低请求频率并实现退避机制。
  • 验证架构:请始终传递严格符合架构要求的参数。当返回的是
    schemaRef
    而非
    input_schema
    时,请使用
    RUBE_GET_TOOL_SCHEMAS
    加载完整的输入架构。

Quick Reference

快速参考

OperationApproach
Find tools
RUBE_SEARCH_TOOLS
with ManyChat-specific use case
Connect
RUBE_MANAGE_CONNECTIONS
with toolkit
many_chat
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
操作实现方式
查找工具使用ManyChat特定的用例调用
RUBE_SEARCH_TOOLS
建立连接使用工具包
many_chat
调用
RUBE_MANAGE_CONNECTIONS
执行操作使用发现的工具标识调用
RUBE_MULTI_EXECUTE_TOOL
批量操作
RUBE_REMOTE_WORKBENCH
中使用
run_composio_tool()
获取完整架构对带有
schemaRef
的工具调用
RUBE_GET_TOOL_SCHEMAS