clevertap-mcp
clevertap-mcp
一个用于 CleverTap REST API 的 模型上下文协议 (MCP) 服务器。它将 CleverTap 的用户画像、事件、营销活动和报告作为工具公开,任何兼容 MCP 的 AI 助手(如 Claude、Cursor 等)都可以直接调用。
功能特性
多项目支持 — 从单个服务器实例管理多个 CleverTap 账户
引导式设置 — 如果未配置项目,
clevertap_configure将引导您完成整个过程全面的 API 覆盖 — 支持事件、画像、营销活动和报告
异步轮询 — 自动轮询长时间运行的操作(事件/画像计数)
Related MCP server: Mixpanel MCP Server
工具
元数据
工具 | 描述 |
| 引导式设置,用于添加项目或生成 |
| 列出所有已配置的项目及其区域 |
事件
工具 | 描述 |
| 为用户上传一个或多个事件 |
| 使用过滤器查询事件数据 |
| 通过游标获取下一页事件结果 |
| 获取事件的总计数(支持异步轮询) |
用户画像
工具 | 描述 |
| 创建或更新用户画像 |
| 通过身份、电子邮件或 objectId 查找单个用户 |
| 获取执行过某事件的用户画像 |
| 通过游标获取下一页画像结果 |
| 删除用户画像 |
| 为用户注册推送令牌 |
| 计算匹配细分市场的画像数量 |
| 拆分已合并的画像 |
| 订阅/取消订阅用户的渠道 |
| 从画像中移除电话号码 |
营销活动
工具 | 描述 |
| 列出日期范围内的营销活动 |
| 获取营销活动的投放和互动统计数据 |
| 停止正在运行的营销活动 |
| 创建并启动营销活动 |
报告
工具 | 描述 |
| 消息级投放报告 |
| 事件的顶级属性值计数 |
| 事件的日/周/月趋势 |
| 日活跃用户趋势 |
| 卸载趋势报告 |
| 实时活跃用户计数 |
通用
工具 | 描述 |
| 发起任何原始 REST API 请求 |
| 通过 |
Web / 浏览器
工具 | 描述 |
| 打开 Chromium 窗口,并在手动登录后捕获仪表板会话 cookie + CSRF 令牌(支持 SSO 和 2FA) |
| 检查是否已为项目捕获 Web 会话,以及获取时间 |
| 使用捕获的会话向任何 CleverTap 仪表板端点发起已认证的请求 |
| 从仪表板 UI API 列出营销活动 — 比 REST API 提供更丰富的数据(状态、发送量、展示量、点击量、编辑 URL) |
| 向特定设备令牌发送测试推送通知。接受来自 |
Web 工具前提条件: 在
npm install后安装一次 Playwright Chromium 二进制文件:npx playwright install chromium
安装
git clone https://github.com/your-org/clevertap-mcp.git
cd clevertap-mcp
npm install
npx playwright install chromium # required for web/browser tools
npm run build配置
服务器从 CLEVERTAP_PROJECTS 环境变量中读取项目凭据 — 这是一个项目对象的 JSON 数组:
[
{
"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"
}
]支持的区域: in1, us1, eu1, sg1, aps3, mec1
单项目回退
您也可以为单个项目使用单独的环境变量:
CLEVERTAP_ACCOUNT_ID=XXX-XXX-XXXX
CLEVERTAP_PASSCODE=YYY-YYY-YYYY
CLEVERTAP_REGION=us1添加到 Claude Desktop
在您的 claude_desktop_config.json(或 ~/.claude.json)中:
{
"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\"}]"
}
}
}
}重要:
CLEVERTAP_PROJECTS必须是env块内序列化的 JSON 字符串(而不是原生 JSON 对象)。
开发
npm run build # compile TypeScript → dist/
npm run dev # watch mode
npm start # run compiled server项目结构
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 # Browser session tools via Playwright (login, campaigns UI, test push)许可证
MIT
Available Tools
1 toolclevertap_configureA
CleverTap MCP has no project configured yet. Call this tool with your CleverTap credentials and it will return the exact configuration snippet to paste into your MCP settings — then restart the server to activate all tools.
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | Yes | CleverTap Account ID — found in the CleverTap dashboard under Settings → Accounts | |
| passcode | Yes | CleverTap Passcode — found in the CleverTap dashboard under Settings → Accounts | |
| region | No | Data residency region: in1 (India), us1 (US), eu1 (Europe), sg1 (Singapore), aps3 (Asia-Pacific), mec1 (Middle East) | in1 |
| project_name | No | Label for this project. Use any short name (e.g. "production", "staging"). Defaults to "default". | default |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains that this tool returns a configuration snippet rather than performing the configuration directly, which is valuable behavioral context. It also mentions the need to restart the server afterward. However, it doesn't disclose potential authentication requirements beyond credentials, rate limits, or error behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with two sentences that each serve a clear purpose: the first establishes the context and action, the second explains the outcome and next steps. There's zero wasted language, and it's front-loaded with the essential information about when and why to use the tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a configuration tool with no annotations and no output schema, the description provides good context about the tool's purpose and usage flow. It explains what happens (returns configuration snippet) and what needs to happen next (restart server). However, it doesn't describe the format of the returned snippet or potential error conditions, leaving some gaps in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents all four parameters thoroughly. The description doesn't add any additional parameter semantics beyond what's in the schema descriptions. It mentions 'credentials' generally but doesn't elaborate on specific parameters. This meets the baseline expectation when schema coverage is complete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action: 'Call this tool with your CleverTap credentials and it will return the exact configuration snippet to paste into your MCP settings.' It explicitly addresses the initial setup scenario ('no project configured yet') and distinguishes this as a one-time configuration tool. The verb 'configure' is specific and the resource is the CleverTap MCP project setup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool: 'CleverTap MCP has no project configured yet.' It also specifies the follow-up action required: 'then restart the server to activate all tools.' Since there are no sibling tools mentioned, the description appropriately focuses on the specific use case without needing to differentiate from alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
clevertap_configure
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it to. The tool's purpose is clearly defined as a configuration setup step.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'clevertap_configure' follows a clear verb_noun pattern, and there are no other tools to create inconsistency.
A single tool is too few for a server intended to interact with CleverTap, as it suggests the server is not yet fully functional or lacks operational capabilities. This is a significant mismatch for the apparent scope of a CleverTap integration.
The tool set is severely incomplete for a CleverTap MCP server, as it only provides a configuration tool and no actual operational tools for interacting with CleverTap data or features. This leaves obvious gaps in the domain coverage.
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
- ZapierOAuthcom.zapier
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that enables AI tools to interact with ActiveCampaign API, allowing contact management and tracking event analysis through natural language queries.51MIT
- AlicenseBqualityDmaintenanceAn MCP server that provides access to the Mixpanel REST API, enabling AI agents to query events, funnels, retention data, and user profiles. It allows users to perform complex analytics tasks and export raw event data through natural language prompts.165 npmMIT
- AlicenseNot gradedqualityBmaintenanceMCP server enabling AI assistants to interact with ClickUp workspaces, including task management, comments, time tracking, and document operations.12 npmMIT
- FlicenseNot gradedqualityCmaintenanceRead-only AI analytics assistant for CleverTap via MCP, enabling querying of events, profiles, campaigns, and realtime data without write endpoints.10 npm-