Skip to main content
Glama
enesjakozh
kapilduraphe

Webflow MCP Server

by kapilduraphe
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Webflow MCP 服务器

铁匠徽章

该 MCP 服务器使 Claude 能够与 Webflow 的 API 进行交互。

先决条件

  • Node.js（v16 或更高版本）

  • 克劳德桌面应用程序

  • Webflow 帐户

  • Webflow API 令牌（站点令牌或 OAuth 访问令牌）

Related MCP server: Webflow

设置说明

1.创建Webflow API令牌

  • 登录您的 Webflow 帐户

  • 导航至“站点设置”>“应用程序和集成”

  • 生成新的 API 令牌

  • 复制令牌值（您将无法再看到它）

或者，您也可以生成 OAuth 访问令牌。

2. 初始项目设置

安装依赖项：

npm install

3.配置环境变量

为本地开发创建一个.env文件（不要提交此文件）：

WEBFLOW_API_TOKEN=your-api-token

4.配置Claude桌面

打开您的 Claude Desktop 配置文件：

对于 MacOS：

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

对于 Windows：

code %AppData%\Claude\claude_desktop_config.json

添加或更新配置：

{
    "mcpServers": {
        "webflow": {
            "command": "node",
            "args": [
                "/ABSOLUTE/PATH/TO/YOUR/build/index.js"
            ],
            "env": {
                "WEBFLOW_API_TOKEN": "your-api-token"
            }
        }
    }
}

保存文件并重新启动 Claude Desktop。

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 Webflow MCP 服务器：

npx -y @smithery/cli install @kapilduraphe/webflow-mcp-server --client claude

可用工具

该服务器目前提供以下工具：

获取站点

检索经过身份验证的用户可访问的所有 Webflow 站点列表。返回的详细信息包括：

  • 站点显示名称和简称

  • 站点 ID 和工作区 ID

  • 创建、上次更新和上次发布日期

  • 预览网址

  • 时区设置

  • 自定义域配置

  • 本地化设置（主要和次要语言环境）

  • 数据收集偏好

获取站点

通过 ID 检索特定 Webflow 站点的详细信息。需要一个 siteId 参数，并返回与 get_sites 相同的单个站点的详细信息。

类型定义

interface WebflowApiError {
    status?: number;
    message: string;
    code?: string;
}

interface WebflowCustomDomain {
    id: string;
    url: string;
    lastPublished: string;
}

interface WebflowLocale {
    id: string;
    cmsLocaleId: string;
    enabled: boolean;
    displayName: string;
    redirect: boolean;
    subdirectory: string;
    tag: string;
}

interface WebflowSite {
    id: string;
    workspaceId: string;
    createdOn: string;
    displayName: string;
    shortName: string;
    lastPublished: string;
    lastUpdated: string;
    previewUrl: string;
    timeZone: string;
    parentFolderId?: string;
    customDomains: WebflowCustomDomain[];
    locales: {
        primary: WebflowLocale;
        secondary: WebflowLocale[];
    };
    dataCollectionEnabled: boolean;
    dataCollectionType: string;
}

错误处理

服务器处理各种错误情况：

环境错误

  • 缺少 WEBFLOW_API_TOKEN

  • API 令牌无效

故障排除

常见问题

Claude 中未出现的工具

  • 检查 Claude Desktop 日志

  • 验证 WEBFLOW_API_TOKEN 是否设置正确

  • 确保 index.js 的路径是绝对的并且正确

身份验证错误

  • 验证您的 API 令牌是否有效

  • 检查令牌是否具有必要的权限

  • 确保令牌未过期

查看日志

查看服务器日志：

对于 MacOS/Linux：

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

对于 Windows：

Get-Content -Path "$env:AppData\Claude\Logs\mcp*.log" -Wait -Tail 20

环境变量

如果您收到环境变量错误，请验证：

  • WEBFLOW_API_TOKEN ：应该是一个有效的 API 令牌

安全注意事项

  • 确保您的 API 令牌安全

  • 不要将凭证提交到版本控制

  • 使用环境变量来存储敏感数据

  • 定期轮换 API 令牌

  • 在 Webflow 中监控 API 使用情况

  • 使用 API 令牌所需的最低权限

支持

如果您遇到任何问题：

  • 查看上面的故障排除部分

  • 查看 Claude Desktop 日志

  • 检查服务器的错误输出

  • 查看 Webflow 的 API 文档

执照

MIT 许可证 - 有关详细信息，请参阅 LICENSE 文件。

Available Tools

2 tools
get_siteA

Retrieve detailed information about a specific Webflow site by ID, including workspace, creation date, display name, and publishing details

ParametersJSON Schema
NameRequiredDescriptionDefault
siteIdYesThe unique identifier of the Webflow site

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the tool as a retrieval operation, which implies read-only behavior, but does not disclose other traits such as authentication requirements, rate limits, error handling, or response format. This leaves significant gaps for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and key details without unnecessary words. It is front-loaded with the main action and resource, making it easy to understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (simple retrieval with one parameter), 100% schema coverage, but no output schema and no annotations, the description is adequate but incomplete. It covers the purpose and parameter semantics well, but lacks behavioral details like response format or error handling, which are important for a tool with no structured output information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the parameter 'siteId' documented as 'The unique identifier of the Webflow site'. The description adds value by specifying that the tool retrieves information 'by ID', reinforcing the parameter's purpose, but does not provide additional syntax or format details beyond what the schema already covers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and the resource 'detailed information about a specific Webflow site by ID', with specific details like workspace, creation date, display name, and publishing details. It distinguishes from the sibling tool 'get_sites' by specifying retrieval for a single site rather than multiple sites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when detailed information for a specific site is needed, but does not explicitly state when to use this tool versus the sibling 'get_sites' or other alternatives. It provides clear context for retrieving site details by ID, but lacks explicit exclusions or comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_sitesB

Retrieve a list of all Webflow sites accessible to the authenticated user

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions authentication requirements, which is useful context. However, it lacks details on behavioral traits such as rate limits, pagination, error handling, or what 'accessible' entails (e.g., permissions, workspace scoping). For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that efficiently conveys the tool's purpose and key constraint (authentication). It is front-loaded with the main action and resource, with no wasted words or redundant information. Every part of the sentence earns its place by adding value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but has clear gaps. It covers the basic purpose and authentication context but lacks details on output format (e.g., structure of the list), error cases, or limitations. Without annotations or output schema, the description should ideally provide more behavioral context to be fully complete for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. A baseline of 4 is applied since no parameters exist, and the description doesn't introduce confusion about inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'retrieve' and resource 'list of all Webflow sites', making the purpose specific and understandable. It distinguishes from the sibling 'get_site' by indicating it returns a list rather than a single site, though it doesn't explicitly name the alternative. The description is not tautological and provides meaningful context about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by specifying 'accessible to the authenticated user', suggesting it should be used when needing all sites the user can access. However, it doesn't provide explicit guidance on when to use this vs. the sibling 'get_site' or other alternatives, nor does it mention any exclusions or prerequisites beyond authentication. The usage context is implied but not fully articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: get_site retrieves detailed information for a specific site by ID, while get_sites lists all accessible sites. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on whether it needs a single site's details or a list of sites.

Naming Consistency5/5

Both tools follow a consistent verb_noun naming pattern (get_site and get_sites), using the same verb 'get' and singular/plural forms of 'site' to indicate scope. This predictable naming makes the tool set easy to understand and use.

Tool Count2/5

With only 2 tools, the server feels severely under-scoped for a Webflow integration, which typically involves managing sites, collections, items, and other resources. This limited set will likely cause agents to hit dead ends when trying to perform common operations like creating or updating sites.

Completeness2/5

The tool set is incomplete for Webflow's domain, covering only read operations (get) for sites. It lacks essential CRUD operations such as create_site, update_site, delete_site, and tools for managing collections, items, or other Webflow resources, creating significant gaps that will hinder agent workflows.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kapilduraphe/webflow-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server