rybbit-mcp
Exposes Rybbit Analytics as MCP tools for querying site traffic, page views, visitor sessions, and live visitor counts through natural language.
README
rybbit-mcp
An MCP server that exposes Rybbit Analytics as tools for Claude (or any MCP-compatible client). Ask Claude things like:
- "What's the traffic overview for my site this week?"
- "What are the top 10 pages by visits this month?"
- "How many people are on the site right now?"
- "Where is my traffic coming from, by country?"
- "Show me the most recent sessions from mobile users."
It works against both Rybbit Cloud (app.rybbit.io) and self-hosted Rybbit instances.
Tools
| Tool | Description |
|---|---|
rybbit_list_sites |
List organizations and sites (with their site IDs) |
rybbit_get_site |
Get config/details for one site |
rybbit_get_overview |
Sessions, pageviews, users, bounce rate, duration for a time range |
rybbit_get_overview_timeseries |
Same metrics bucketed over time (for trend charts) |
rybbit_get_breakdown |
Top pages, referrers, countries, browsers, devices, UTM params, etc. |
rybbit_get_live_visitors |
Current active visitor count |
rybbit_list_sessions |
Paginated list of visitor sessions |
rybbit_get_session |
Full detail + event list for one session |
rybbit_get_session_locations |
Aggregated session geolocation, for mapping |
This covers Rybbit's Overview and Sessions API families. The same client/tool pattern can be extended to Events, Users, Goals, Funnels, Performance, and Errors — see Extending below.
Setup
1. Get a Rybbit API key
In your Rybbit dashboard: Settings → Account → API Keys → Create.
Self-hosted instances have no rate limits. Rybbit Cloud rate-limits API keys per your plan (Standard: 20 req/min, Pro: 200 req/min); Free/Basic plans don't get API key access.
2. Build the server
git clone https://github.com/<your-username>/rybbit-mcp.git
cd rybbit-mcp
npm install
npm run build
This produces build/index.js.
3. Configure your MCP client
Claude Desktop / Claude Code — add to your MCP config (claude_desktop_config.json or .claude/settings.json):
{
"mcpServers": {
"rybbit": {
"command": "node",
"args": ["/absolute/path/to/rybbit-mcp/build/index.js"],
"env": {
"RYBBIT_URL": "https://app.rybbit.io",
"RYBBIT_API_KEY": "your-api-key-here"
}
}
}
}
If you self-host Rybbit, set RYBBIT_URL to your instance's base URL instead (e.g. https://analytics.yourdomain.com).
Restart Claude Desktop / reload Claude Code, and the rybbit_* tools should appear.
Deploying to CapRover (or Docker)
This MCP server supports Server-Sent Events (SSE) for remote clients over HTTP. This is perfect for deploying to a platform like CapRover so that a remote AI agent can access the tools.
- Create a new App in your CapRover dashboard (e.g.,
rybbit-mcp). - Set the Environment Variables in CapRover:
RYBBIT_URLRYBBIT_API_KEYPORT=3000(Optional, defaults to 3000)
- Under the Deployment tab, deploy using the Captain Definition or simply push this repository via the CapRover CLI. This repository contains a
Dockerfilethat CapRover will automatically detect and build.
Once deployed, the SSE endpoint will be available at:
https://rybbit-mcp.your-caprover-domain.com/sse
Your remote AI agents can connect to this URL via SSEServerTransport instead of stdio.
4. Try it
"Use rybbit to show me an overview of site 123 for the last 7 days" "What are the top pages on my site this month?" "How many live visitors do I have right now?"
Development
npm run watch # recompile on change
npm run inspector # open the MCP Inspector against this server
Extending
Rybbit's API has more endpoint families than this v1 covers (Events, Users, Goals, Funnels, Performance metrics, Errors — see the Rybbit API docs). To add one:
- Add a method to
src/rybbit-client.tscalling the endpoint. - Register a corresponding tool in
src/index.tswithserver.registerTool(...), usingzodfor the input schema. npm run buildand reload your MCP client.
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。