clevertap-mcp

clevertap-mcp

An MCP server that enables AI assistants to interact with the CleverTap REST API to manage user profiles, events, campaigns, and reports. It supports multi-project configurations and provides tools for data analysis and campaign management through natural language.

Category
访问服务器

README

clevertap-mcp

A Model Context Protocol (MCP) server for the CleverTap REST API. Exposes CleverTap's user profiles, events, campaigns, and reports as tools that any MCP-compatible AI assistant (Claude, Cursor, etc.) can call directly.


Features

  • Multi-project — manage multiple CleverTap accounts from a single server instance
  • Guided setup — if no project is configured, clevertap_configure walks you through the process
  • Full API coverage — events, profiles, campaigns, and reports
  • Async polling — long-running operations (event/profile counts) are polled automatically

Tools

Meta

Tool Description
clevertap_configure Guided setup to add a project or generate the CLEVERTAP_PROJECTS config
clevertap_list_projects List all configured projects and their regions

Events

Tool Description
clevertap_upload_events Upload one or more events for a user
clevertap_get_events Query event data with filters
clevertap_get_events_cursor Fetch the next page of event results via cursor
clevertap_get_event_count Get the total count of an event (with async polling)

Profiles

Tool Description
clevertap_upload_profiles Create or update user profiles
clevertap_get_profile Look up a single user by identity, email, or objectId
clevertap_get_profiles_by_event Get profiles of users who performed an event
clevertap_get_profiles_cursor Fetch the next page of profile results via cursor
clevertap_delete_profile Delete a user profile
clevertap_upload_device_token Register a push token for a user
clevertap_get_profile_count Count profiles matching a segment
clevertap_demerge_profiles Split merged profiles apart
clevertap_subscribe Subscribe/unsubscribe a user to channels
clevertap_disassociate_phone Remove a phone number from a profile

Campaigns

Tool Description
clevertap_get_campaigns List campaigns within a date range
clevertap_get_campaign_report Get delivery and engagement stats for a campaign
clevertap_stop_campaign Stop a running campaign
clevertap_create_campaign Create and launch a campaign

Reports

Tool Description
clevertap_get_message_report Message-level delivery report
clevertap_get_top_property_count Top property value counts for an event
clevertap_get_event_trend Daily/weekly/monthly trend for an event
clevertap_get_dau Daily active users trend
clevertap_get_uninstall_report Uninstall trend report
clevertap_get_real_time_counts Real-time active user counts

Generic

Tool Description
clevertap_request Make any raw REST API request
clevertap_poll Poll a pending async request by req_id

Installation

git clone https://github.com/your-org/clevertap-mcp.git
cd clevertap-mcp
npm install
npm run build

Configuration

The server reads project credentials from the CLEVERTAP_PROJECTS environment variable — a JSON array of project objects:

[
  {
    "name": "My App - Production",
    "account_id": "XXX-XXX-XXXX",
    "passcode": "YYY-YYY-YYYY",
    "region": "us1"
  },
  {
    "name": "My App - Staging",
    "account_id": "AAA-AAA-AAAA",
    "passcode": "BBB-BBB-BBBB",
    "region": "us1"
  }
]

Supported regions: in1, us1, eu1, sg1, aps3, mec1

Single-project fallback

You can also use individual environment variables for a single project:

CLEVERTAP_ACCOUNT_ID=XXX-XXX-XXXX
CLEVERTAP_PASSCODE=YYY-YYY-YYYY
CLEVERTAP_REGION=us1

Adding to Claude Desktop

In your claude_desktop_config.json (or ~/.claude.json):

{
  "mcpServers": {
    "clevertap": {
      "command": "node",
      "args": ["/absolute/path/to/clevertap-mcp/dist/index.js"],
      "env": {
        "CLEVERTAP_PROJECTS": "[{\"name\":\"My App\",\"account_id\":\"XXX-XXX-XXXX\",\"passcode\":\"YYY-YYY-YYYY\",\"region\":\"us1\"}]"
      }
    }
  }
}

Important: CLEVERTAP_PROJECTS must be a serialized JSON string (not a native JSON object) inside the env block.


Development

npm run build      # compile TypeScript → dist/
npm run dev        # watch mode
npm start          # run compiled server

Project structure

src/
  index.ts          # MCP server entry point, project config, tool registration
  client.ts         # CleverTap REST API HTTP client
  tools/
    events.ts       # Event upload and query tools
    profiles.ts     # Profile management tools
    campaigns.ts    # Campaign tools
    reports.ts      # Analytics and report tools
    generic.ts      # Raw request / poll tools
    web.ts          # (future) Browser session tools via Playwright

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选