wireboard-mcp
Enables LLM agents to query real-time and historical analytics from WireBoard, allowing natural language questions about visitors, events, and site metrics.
README
<p align="center"> <a href="https://wireboard.io"> <img src="https://wireboard.io/img/logo-blue.png" alt="WireBoard" height="64"> </a> </p>
<h1 align="center"><code>wireboard-mcp</code></h1>
<p align="center"> Official Model Context Protocol server for <a href="https://wireboard.io">WireBoard</a>. </p>
<p align="center"> Lets LLM agents (Claude Desktop, Cursor, VS Code, etc.) query your real-time and historical analytics in conversation. Built on top of the official <a href="https://www.npmjs.com/package/@wireboard/api"><code>@wireboard/api</code></a> JavaScript SDK. </p>
Install
Two ways to install, pick whichever fits your setup.
Option A: Desktop Extension (recommended for Claude Desktop users)
Download wireboard-mcp-x.y.z.mcpb from the GitHub releases page and double-click it. One file works on Windows, macOS, and Linux — Claude Desktop ships its own Node runtime, so there are no system dependencies to install.
Claude Desktop will prompt for your WireBoard API token, store it securely in your OS keychain, and the WireBoard tools become available immediately.
If double-click doesn't open the file, install it via Claude Desktop → Settings → Extensions → Advanced Settings → Install Extension.
Option B: npm install (for Cursor, VS Code, headless / CI, automation)
npm install -g @wireboard/mcp
Requires Node 18+. Then configure your MCP client of choice.
Claude Desktop config
Edit claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"wireboard": {
"command": "wireboard-mcp",
"env": {
"WIREBOARD_TOKEN": "your_token_here"
}
}
}
}
Restart Claude Desktop. The WireBoard tools will appear automatically.
Cursor / VS Code / other MCP clients
Use the same command + env-var pattern in your client's MCP config.
Mint a token
You need a WireBoard API token before either install path will work. Mint one at Settings → API with the analytics:read ability for REST tools and live:read for the live snapshot tool.
What you can ask
Once configured, ask Claude things like:
- "How many visitors did my site get last week?"
- "Show me the top 10 referrers for the past 30 days."
- "What's happening on my site right now?"
- "Which pages under /checkout have the worst bounce rate this month?"
- "How many Purchase events fired from utm_source=newsletter yesterday?"
- "Compare visitor counts day by day for the past two weeks."
Claude will pick the right tool, call it, and answer in natural language.
Available tools
| Tool | What |
|---|---|
list_sites |
Every site in the account |
get_account |
Token-owner identity + abilities |
get_aggregate |
Period totals: visitors, pageviews, bounce rate, duration |
get_timeseries |
One metric (visitors or pageviews) bucketed by hour or day |
get_history |
Per-day visitors / returning / pageviews / bounce / duration |
get_breakdown |
Top-N rows by dimension (country, device, browser, referrer, etc.) |
get_top_urls |
Per-URL metrics with prefix / contains / exact filters |
query_events |
Custom event queries with grouping and filtering |
get_live_state |
Real-time snapshot (live visitor count, top pages, active sessions, etc.) |
list_dimensions |
Meta: every dimension, metric, and limit the API supports |
All tools accept natural date ranges: "today", "yesterday", "last 7 days" (or "30d" shorthand), "this week", "last week", "this month", "last month", or explicit "YYYY-MM-DD..YYYY-MM-DD". Always UTC.
Rate limiting
The MCP proactively caps itself at 100 requests/minute (under the API's 120/minute limit) so LLM bursts space themselves out instead of hitting 429s. Override with the WIREBOARD_MCP_RATE_PER_MINUTE env var if you have a use case that needs different pacing.
The underlying SDK still auto-retries on 429 as a backstop.
Security
- Treat your token like a credential. It has full
analytics:readandlive:readscope on every site in the account. - Don't commit your MCP client config to a public repo with the token in it. Use an env var or a secret manager and reference it from your config.
- Revoke and rotate if a token leaks. Settings → API in your dashboard.
The MCP is read-only: it can fetch data, never modify it. The WireBoard public API itself is read-only in v1.
Logging
Logs go to stderr (so they don't interfere with the MCP protocol on stdout).
Source and contributing
- npm:
@wireboard/mcp - Repository:
github.com/wireboard/mcp - Releases (.mcpb downloads):
github.com/wireboard/mcp/releases - Issues:
github.com/wireboard/mcp/issues - Underlying SDK:
@wireboard/api(source) - WireBoard docs: https://wireboard.io/docs/api-overview
Building locally
npm install
npm test # run vitest
npm run build # bundle TS → dist/index.js (esbuild, ~600 KB)
npm run build:mcpb # also pack dist/wireboard-mcp-<version>.mcpb
The .mcpb is a zip of manifest.json, icon.png, and the single bundled dist/index.js. All runtime dependencies are inlined by esbuild.
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。