webflow-automation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Webflow Automation via Rube MCP

通过Rube MCP实现Webflow自动化

Automate Webflow operations including CMS collection management, site publishing, page inspection, asset uploads, and ecommerce order retrieval through Composio's Webflow toolkit.
借助Composio的Webflow工具包,实现Webflow操作自动化,包括CMS集合管理、站点发布、页面检查、资源上传和电商订单检索。

Prerequisites

前提条件

  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Webflow connection via
    RUBE_MANAGE_CONNECTIONS
    with toolkit
    webflow
  • Always call
    RUBE_SEARCH_TOOLS
    first to get current tool schemas
  • 必须已连接Rube MCP(需提供RUBE_SEARCH_TOOLS)
  • 通过
    RUBE_MANAGE_CONNECTIONS
    并使用工具包
    webflow
    完成Webflow的激活连接
  • 请始终先调用
    RUBE_SEARCH_TOOLS
    以获取最新的工具模式

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
    webflow
  3. If connection is not ACTIVE, follow the returned auth link to complete Webflow OAuth
  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,只需添加端点即可使用。
  1. 确认
    RUBE_SEARCH_TOOLS
    可响应,以此验证Rube MCP是否可用
  2. 调用
    RUBE_MANAGE_CONNECTIONS
    并指定工具包
    webflow
  3. 如果连接状态未显示为ACTIVE,请按照返回的授权链接完成Webflow OAuth认证
  4. 在运行任何工作流之前,确认连接状态为ACTIVE

Core Workflows

核心工作流

1. Manage CMS Collection Items

1. 管理CMS集合项

When to use: User wants to create, update, list, or delete items in Webflow CMS collections (blog posts, products, team members, etc.)
Tool sequence:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - List sites to find the target site_id [Prerequisite]
  2. WEBFLOW_LIST_COLLECTIONS
    - List all collections for the site [Prerequisite]
  3. WEBFLOW_GET_COLLECTION
    - Get collection schema to find valid field slugs [Prerequisite for create/update]
  4. WEBFLOW_LIST_COLLECTION_ITEMS
    - List existing items with filtering and pagination [Optional]
  5. WEBFLOW_GET_COLLECTION_ITEM
    - Get a specific item's full details [Optional]
  6. WEBFLOW_CREATE_COLLECTION_ITEM
    - Create a new item with field data [Required for creation]
  7. WEBFLOW_UPDATE_COLLECTION_ITEM
    - Update an existing item's fields [Required for updates]
  8. WEBFLOW_DELETE_COLLECTION_ITEM
    - Permanently remove an item [Optional]
  9. WEBFLOW_PUBLISH_SITE
    - Publish changes to make them live [Optional]
Key parameters for CREATE_COLLECTION_ITEM:
  • collection_id
    : 24-character hex string from LIST_COLLECTIONS
  • field_data
    : Object with field slug keys (NOT display names); must include
    name
    and
    slug
  • field_data.name
    : Display name for the item
  • field_data.slug
    : URL-friendly identifier (lowercase, hyphens, no spaces)
  • is_draft
    : Boolean to create as draft (default false)
Key parameters for UPDATE_COLLECTION_ITEM:
  • collection_id
    : Collection identifier
  • item_id
    : 24-character hex MongoDB ObjectId of the existing item
  • fields
    : Object with field slug keys and new values
  • live
    : Boolean to publish changes immediately (default false)
Field value types:
  • Text/Email/Link/Date: string
  • Number: integer or float
  • Boolean: true/false
  • Image:
    {"url": "...", "alt": "...", "fileId": "..."}
  • Multi-reference: array of reference ID strings
  • Multi-image: array of image objects
  • Option: option ID string
Pitfalls:
  • Field keys must use the exact field
    slug
    from the collection schema, NOT display names
  • Always call
    GET_COLLECTION
    first to retrieve the schema and identify correct field slugs
  • CREATE_COLLECTION_ITEM
    requires
    name
    and
    slug
    in
    field_data
  • UPDATE_COLLECTION_ITEM
    cannot create new items; it requires a valid existing
    item_id
  • item_id
    must be a 24-character hexadecimal MongoDB ObjectId
  • Slug must be lowercase alphanumeric with hyphens:
    ^[a-z0-9]+(?:-[a-z0-9]+)*$
  • CMS items are staged; use
    PUBLISH_SITE
    or set
    live: true
    to push to production
适用场景:用户需要在Webflow CMS集合(博客文章、产品、团队成员等)中创建、更新、列出或删除项
工具执行顺序:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - 列出站点以找到目标site_id [前置条件]
  2. WEBFLOW_LIST_COLLECTIONS
    - 列出该站点的所有集合 [前置条件]
  3. WEBFLOW_GET_COLLECTION
    - 获取集合模式以找到有效的字段别名 [创建/更新操作的前置条件]
  4. WEBFLOW_LIST_COLLECTION_ITEMS
    - 列出现有项,支持筛选和分页 [可选]
  5. WEBFLOW_GET_COLLECTION_ITEM
    - 获取特定项的完整详情 [可选]
  6. WEBFLOW_CREATE_COLLECTION_ITEM
    - 使用字段数据创建新项 [创建操作必填]
  7. WEBFLOW_UPDATE_COLLECTION_ITEM
    - 更新现有项的字段 [更新操作必填]
  8. WEBFLOW_DELETE_COLLECTION_ITEM
    - 永久删除项 [可选]
  9. WEBFLOW_PUBLISH_SITE
    - 发布更改使其生效 [可选]
CREATE_COLLECTION_ITEM的关键参数:
  • collection_id
    : 来自LIST_COLLECTIONS的24位十六进制字符串
  • field_data
    : 包含字段别名键的对象(而非显示名称);必须包含
    name
    slug
  • field_data.name
    : 项的显示名称
  • field_data.slug
    : URL友好的标识符(小写、连字符分隔、无空格)
  • is_draft
    : 布尔值,设置是否以草稿形式创建(默认false)
UPDATE_COLLECTION_ITEM的关键参数:
  • collection_id
    : 集合标识符
  • item_id
    : 现有项的24位十六进制MongoDB ObjectId
  • fields
    : 包含字段别名键和新值的对象
  • live
    : 布尔值,设置是否立即发布更改(默认false)
字段值类型:
  • 文本/邮箱/链接/日期: 字符串
  • 数字: 整数或浮点数
  • 布尔值: true/false
  • 图片:
    {"url": "...", "alt": "...", "fileId": "..."}
  • 多引用: 引用ID字符串数组
  • 多图片: 图片对象数组
  • 选项: 选项ID字符串
常见陷阱:
  • 字段键必须使用集合模式中的精确字段
    slug
    ,而非显示名称
  • 请始终先调用
    GET_COLLECTION
    以获取模式,确认正确的字段别名
  • CREATE_COLLECTION_ITEM
    要求
    field_data
    中包含
    name
    slug
  • UPDATE_COLLECTION_ITEM
    无法创建新项,必须提供有效的现有
    item_id
  • item_id
    必须是24位十六进制的MongoDB ObjectId
  • Slug必须是小写字母数字加连字符,符合正则:
    ^[a-z0-9]+(?:-[a-z0-9]+)*$
  • CMS项为暂存状态;需使用
    PUBLISH_SITE
    或设置
    live: true
    才能推送到生产环境

2. Manage Sites and Publishing

2. 管理站点与发布

When to use: User wants to list sites, inspect site configuration, or publish staged changes
Tool sequence:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - List all accessible sites [Required]
  2. WEBFLOW_GET_SITE_INFO
    - Get detailed site metadata including domains and settings [Optional]
  3. WEBFLOW_PUBLISH_SITE
    - Deploy all staged changes to live site [Required for publishing]
Key parameters for PUBLISH_SITE:
  • site_id
    : Site identifier from LIST_WEBFLOW_SITES
  • custom_domains
    : Array of custom domain ID strings (from GET_SITE_INFO)
  • publish_to_webflow_subdomain
    : Boolean to publish to
    {shortName}.webflow.io
  • At least one of
    custom_domains
    or
    publish_to_webflow_subdomain
    must be specified
Pitfalls:
  • PUBLISH_SITE
    republishes ALL staged changes for selected domains -- verify no unintended drafts are pending
  • Rate limit: 1 successful publish per minute
  • For sites without custom domains, must set
    publish_to_webflow_subdomain: true
  • custom_domains
    expects domain IDs (hex strings), not domain names
  • Publishing is a production action -- always confirm with the user first
适用场景:用户需要列出站点、检查站点配置或发布暂存更改
工具执行顺序:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - 列出所有可访问的站点 [必填]
  2. WEBFLOW_GET_SITE_INFO
    - 获取站点的详细元数据,包括域名和设置 [可选]
  3. WEBFLOW_PUBLISH_SITE
    - 将所有暂存更改部署到线上站点 [发布操作必填]
PUBLISH_SITE的关键参数:
  • site_id
    : 来自LIST_WEBFLOW_SITES的站点标识符
  • custom_domains
    : 自定义域名ID字符串数组(来自GET_SITE_INFO)
  • publish_to_webflow_subdomain
    : 布尔值,设置是否发布到
    {shortName}.webflow.io
  • 必须指定
    custom_domains
    publish_to_webflow_subdomain
    中的至少一个
常见陷阱:
  • PUBLISH_SITE
    会重新发布所选域名的所有暂存更改——请确认没有未预期的草稿待处理
  • 速率限制:每分钟仅允许1次成功发布
  • 对于无自定义域名的站点,必须设置
    publish_to_webflow_subdomain: true
  • custom_domains
    需要域名ID(十六进制字符串),而非域名名称
  • 发布是影响生产环境的操作——请始终先与用户确认

3. Manage Pages

3. 管理页面

When to use: User wants to list pages, inspect page metadata, or examine page DOM structure
Tool sequence:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - Find the target site_id [Prerequisite]
  2. WEBFLOW_LIST_PAGES
    - List all pages for a site with pagination [Required]
  3. WEBFLOW_GET_PAGE
    - Get detailed metadata for a specific page [Optional]
  4. WEBFLOW_GET_PAGE_DOM
    - Get the DOM/content node structure of a static page [Optional]
Key parameters:
  • site_id
    : Site identifier (required for list pages)
  • page_id
    : 24-character hex page identifier
  • locale_id
    : Optional locale filter for multi-language sites
  • limit
    : Max results per page (max 100)
  • offset
    : Pagination offset
Pitfalls:
  • LIST_PAGES
    paginates via offset/limit; iterate when sites have many pages
  • Page IDs are 24-character hex strings matching pattern
    ^[0-9a-fA-F]{24}$
  • GET_PAGE_DOM
    returns the node structure, not rendered HTML
  • Pages include both static and CMS-driven pages
适用场景:用户需要列出页面、检查页面元数据或查看页面DOM结构
工具执行顺序:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - 找到目标site_id [前置条件]
  2. WEBFLOW_LIST_PAGES
    - 列出站点的所有页面,支持分页 [必填]
  3. WEBFLOW_GET_PAGE
    - 获取特定页面的详细元数据 [可选]
  4. WEBFLOW_GET_PAGE_DOM
    - 获取静态页面的DOM/内容节点结构 [可选]
关键参数:
  • site_id
    : 站点标识符(列出页面时必填)
  • page_id
    : 24位十六进制页面标识符
  • locale_id
    : 多语言站点的可选区域筛选器
  • limit
    : 每页最大结果数(最大100)
  • offset
    : 分页偏移量
常见陷阱:
  • LIST_PAGES
    通过offset/limit实现分页;当站点页面较多时需循环迭代
  • 页面ID是符合正则
    ^[0-9a-fA-F]{24}$
    的24位十六进制字符串
  • GET_PAGE_DOM
    返回节点结构,而非渲染后的HTML
  • 页面包括静态页面和CMS驱动的页面

4. Upload Assets

4. 上传资源

When to use: User wants to upload images, files, or other assets to a Webflow site
Tool sequence:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - Find the target site_id [Prerequisite]
  2. WEBFLOW_UPLOAD_ASSET
    - Upload a file with base64-encoded content [Required]
Key parameters:
  • site_id
    : Site identifier
  • file_name
    : Name of the file (e.g.,
    "logo.png"
    )
  • file_content
    : Base64-encoded binary content of the file (NOT a placeholder or URL)
  • content_type
    : MIME type (e.g.,
    "image/png"
    ,
    "image/jpeg"
    ,
    "application/pdf"
    )
  • md5
    : MD5 hash of the raw file bytes (32-character hex string)
  • asset_folder_id
    : Optional folder placement
Pitfalls:
  • file_content
    must be actual base64-encoded data, NOT a variable reference or placeholder
  • md5
    must be computed from the raw bytes, not from the base64 string
  • This is a two-step process internally: generates an S3 pre-signed URL, then uploads
  • Large files may encounter timeouts; keep uploads reasonable in size
适用场景:用户需要将图片、文件或其他资源上传到Webflow站点
工具执行顺序:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - 找到目标site_id [前置条件]
  2. WEBFLOW_UPLOAD_ASSET
    - 上传Base64编码的文件内容 [必填]
关键参数:
  • site_id
    : 站点标识符
  • file_name
    : 文件名(例如
    "logo.png"
  • file_content
    : 文件的Base64编码二进制内容(而非占位符或URL)
  • content_type
    : MIME类型(例如
    "image/png"
    ,
    "image/jpeg"
    ,
    "application/pdf"
  • md5
    : 原始文件字节的MD5哈希值(32位十六进制字符串)
  • asset_folder_id
    : 可选的文件夹位置
常见陷阱:
  • file_content
    必须是实际的Base64编码数据,而非变量引用或占位符
  • md5
    必须从原始字节计算,而非从Base64字符串计算
  • 内部为两步流程:生成S3预签名URL,然后上传
  • 大文件可能会超时;请控制上传文件的大小

5. Manage Ecommerce Orders

5. 管理电商订单

When to use: User wants to view ecommerce orders from a Webflow site
Tool sequence:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - Find the site with ecommerce enabled [Prerequisite]
  2. WEBFLOW_LIST_ORDERS
    - List all orders with optional status filtering [Required]
  3. WEBFLOW_GET_ORDER
    - Get detailed information for a specific order [Optional]
Key parameters:
  • site_id
    : Site identifier (must have ecommerce enabled)
  • order_id
    : Specific order identifier for detailed retrieval
  • status
    : Filter orders by status
Pitfalls:
  • Ecommerce must be enabled on the Webflow site for order endpoints to work
  • Order endpoints are read-only; no create/update/delete for orders through these tools
适用场景:用户需要查看Webflow站点的电商订单
工具执行顺序:
  1. WEBFLOW_LIST_WEBFLOW_SITES
    - 找到启用电商功能的站点 [前置条件]
  2. WEBFLOW_LIST_ORDERS
    - 列出所有订单,支持按状态筛选 [必填]
  3. WEBFLOW_GET_ORDER
    - 获取特定订单的详细信息 [可选]
关键参数:
  • site_id
    : 站点标识符(必须已启用电商功能)
  • order_id
    : 特定订单的标识符,用于获取详情
  • status
    : 按状态筛选订单
常见陷阱:
  • 必须在Webflow站点上启用电商功能,订单端点才能正常工作
  • 订单端点为只读;无法通过这些工具创建/更新/删除订单

Common Patterns

通用模式

ID Resolution

ID解析

Webflow uses 24-character hexadecimal IDs throughout:
  • Site ID:
    WEBFLOW_LIST_WEBFLOW_SITES
    -- find by name, capture
    id
  • Collection ID:
    WEBFLOW_LIST_COLLECTIONS
    with
    site_id
  • Item ID:
    WEBFLOW_LIST_COLLECTION_ITEMS
    with
    collection_id
  • Page ID:
    WEBFLOW_LIST_PAGES
    with
    site_id
  • Domain IDs:
    WEBFLOW_GET_SITE_INFO
    -- found in
    customDomains
    array
  • Field slugs:
    WEBFLOW_GET_COLLECTION
    -- found in collection
    fields
    array
Webflow全程使用24位十六进制ID:
  • 站点ID:
    WEBFLOW_LIST_WEBFLOW_SITES
    -- 按名称查找,获取
    id
  • 集合ID: 传入
    site_id
    调用
    WEBFLOW_LIST_COLLECTIONS
    获取
  • 项ID: 传入
    collection_id
    调用
    WEBFLOW_LIST_COLLECTION_ITEMS
    获取
  • 页面ID: 传入
    site_id
    调用
    WEBFLOW_LIST_PAGES
    获取
  • 域名ID:
    WEBFLOW_GET_SITE_INFO
    -- 在
    customDomains
    数组中查找
  • 字段别名:
    WEBFLOW_GET_COLLECTION
    -- 在集合
    fields
    数组中查找

Pagination

分页

Webflow uses offset-based pagination:
  • offset
    : Starting index (0-based)
  • limit
    : Items per page (max 100)
  • Increment offset by limit until fewer results than limit are returned
  • Available on: LIST_COLLECTION_ITEMS, LIST_PAGES
Webflow使用基于偏移量的分页:
  • offset
    : 起始索引(从0开始)
  • limit
    : 每页项数(最大100)
  • 每次将偏移量增加limit,直到返回的结果数少于limit
  • 支持分页的工具:LIST_COLLECTION_ITEMS、LIST_PAGES

CMS Workflow

CMS工作流

Typical CMS content creation flow:
  1. Get site_id from LIST_WEBFLOW_SITES
  2. Get collection_id from LIST_COLLECTIONS
  3. Get field schema from GET_COLLECTION (to learn field slugs)
  4. Create/update items using correct field slugs
  5. Publish site to make changes live
典型的CMS内容创建流程:
  1. 从LIST_WEBFLOW_SITES获取site_id
  2. 从LIST_COLLECTIONS获取collection_id
  3. 从GET_COLLECTION获取字段模式(了解字段别名)
  4. 使用正确的字段别名创建/更新项
  5. 发布站点使更改生效

Known Pitfalls

已知陷阱

ID Formats

ID格式

  • All Webflow IDs are 24-character hexadecimal strings (MongoDB ObjectIds)
  • Example:
    580e63fc8c9a982ac9b8b745
  • Pattern:
    ^[0-9a-fA-F]{24}$
  • Invalid IDs return 404 errors
  • 所有Webflow ID均为24位十六进制字符串(MongoDB ObjectIds)
  • 示例:
    580e63fc8c9a982ac9b8b745
  • 正则模式:
    ^[0-9a-fA-F]{24}$
  • 无效ID会返回404错误

Field Slugs vs Display Names

字段别名与显示名称

  • CMS operations require field
    slug
    values, NOT display names
  • A field with displayName "Author Name" might have slug
    author-name
  • Always call
    GET_COLLECTION
    to discover correct field slugs
  • Using wrong field names silently ignores the data or causes validation errors
  • CMS操作需要字段
    slug
    值,而非显示名称
  • 显示名称为“Author Name”的字段,其别名可能为
    author-name
  • 请始终调用
    GET_COLLECTION
    以确认正确的字段别名
  • 使用错误的字段名称会导致数据被静默忽略或触发验证错误

Publishing

发布

  • PUBLISH_SITE
    deploys ALL staged changes, not just specific items
  • Rate limited to 1 publish per minute
  • Must specify at least one domain target (custom or webflow subdomain)
  • This is a production-affecting action; always confirm intent
  • PUBLISH_SITE
    会部署所有暂存更改,而非仅特定项
  • 速率限制为每分钟1次发布
  • 必须指定至少一个域名目标(自定义域名或Webflow子域名)
  • 这是影响生产环境的操作;请始终确认用户意图

Authentication Scopes

认证权限

  • Different operations require different OAuth scopes:
    sites:read
    ,
    cms:read
    ,
    cms:write
    ,
    pages:read
  • A 403 error typically means missing OAuth scopes
  • Check connection permissions if operations fail with authorization errors
  • 不同操作需要不同的OAuth权限:
    sites:read
    cms:read
    cms:write
    pages:read
  • 403错误通常表示缺少OAuth权限
  • 如果操作因授权错误失败,请检查连接权限

Destructive Operations

破坏性操作

  • DELETE_COLLECTION_ITEM
    permanently removes CMS items
  • PUBLISH_SITE
    makes all staged changes live immediately
  • Always confirm with the user before executing these actions
  • DELETE_COLLECTION_ITEM
    会永久删除CMS项
  • PUBLISH_SITE
    会立即将所有暂存更改发布到线上
  • 执行这些操作前请始终与用户确认

Quick Reference

快速参考

TaskTool SlugKey Params
List sites
WEBFLOW_LIST_WEBFLOW_SITES
(none)
Get site info
WEBFLOW_GET_SITE_INFO
site_id
Publish site
WEBFLOW_PUBLISH_SITE
site_id
,
custom_domains
or
publish_to_webflow_subdomain
List collections
WEBFLOW_LIST_COLLECTIONS
site_id
Get collection schema
WEBFLOW_GET_COLLECTION
collection_id
List collection items
WEBFLOW_LIST_COLLECTION_ITEMS
collection_id
,
limit
,
offset
Get collection item
WEBFLOW_GET_COLLECTION_ITEM
collection_id
,
item_id
Create collection item
WEBFLOW_CREATE_COLLECTION_ITEM
collection_id
,
field_data
Update collection item
WEBFLOW_UPDATE_COLLECTION_ITEM
collection_id
,
item_id
,
fields
Delete collection item
WEBFLOW_DELETE_COLLECTION_ITEM
collection_id
,
item_id
List pages
WEBFLOW_LIST_PAGES
site_id
,
limit
,
offset
Get page
WEBFLOW_GET_PAGE
page_id
Get page DOM
WEBFLOW_GET_PAGE_DOM
page_id
Upload asset
WEBFLOW_UPLOAD_ASSET
site_id
,
file_name
,
file_content
,
content_type
,
md5
List orders
WEBFLOW_LIST_ORDERS
site_id
,
status
Get order
WEBFLOW_GET_ORDER
site_id
,
order_id
任务工具标识关键参数
列出站点
WEBFLOW_LIST_WEBFLOW_SITES
获取站点信息
WEBFLOW_GET_SITE_INFO
site_id
发布站点
WEBFLOW_PUBLISH_SITE
site_id
custom_domains
publish_to_webflow_subdomain
列出集合
WEBFLOW_LIST_COLLECTIONS
site_id
获取集合模式
WEBFLOW_GET_COLLECTION
collection_id
列出集合项
WEBFLOW_LIST_COLLECTION_ITEMS
collection_id
limit
offset
获取集合项
WEBFLOW_GET_COLLECTION_ITEM
collection_id
item_id
创建集合项
WEBFLOW_CREATE_COLLECTION_ITEM
collection_id
field_data
更新集合项
WEBFLOW_UPDATE_COLLECTION_ITEM
collection_id
item_id
fields
删除集合项
WEBFLOW_DELETE_COLLECTION_ITEM
collection_id
item_id
列出页面
WEBFLOW_LIST_PAGES
site_id
limit
offset
获取页面
WEBFLOW_GET_PAGE
page_id
获取页面DOM
WEBFLOW_GET_PAGE_DOM
page_id
上传资源
WEBFLOW_UPLOAD_ASSET
site_id
file_name
file_content
content_type
md5
列出订单
WEBFLOW_LIST_ORDERS
site_id
status
获取订单
WEBFLOW_GET_ORDER
site_id
order_id