How are answers generated, and are they reliable?
Answers are computed from your data and CI‑checked to match the dashboard. No SQL is generated or executed, so results are consistent with your analytics UI.
@Arjun0606
基本信息
self-hosted product + web analytics in one go binary. ask it questions from claude code / cursor over mcp, get exact computed numbers (not hallucinated sql). mit, your data stays on your box.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"smolanalytics": {
"command": "smolanalytics",
"args": [
"mcp"
],
"env": {
"SMOLANALYTICS_DB": "/path/to/events.log"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
smolanalytics is product and web analytics delivered as a single Go binary (MIT). Its MCP server lets you ask analytics questions—like "did activation improve this week?"—directly from your editor (Cursor, Claude Code), with answers computed and CI‑checked to match the dashboard.
Install the single binary or run the demo with docker run -p 8080:8080 ghcr.io/arjun0606/smoleanalytics demo. Connect as a remote MCP server via streamable HTTP at POST https://YOUR_HOST/mcp with Authorization: Bearer <write key>. In your editor, ask natural‑language questions; the server returns verified answers without generating SQL.
Answers are computed from your data and CI‑checked to match the dashboard. No SQL is generated or executed, so results are consistent with your analytics UI.
No. Data never leaves your box; the server runs locally and processes everything in‑memory.
The server exposes 47 tools covering funnels, retention, paths, cohorts, web analytics, GSC, and alerts, plus 13 built‑in prompts.
Run the demo with one command: `docker run -p 8080:8080 ghcr.io/arjun0606/smoleanalytics demo`.
The remote MCP server uses streamable HTTP at `POST https://YOUR_HOST/mcp` with `Authorization: Bearer <write key>`. No other transports are documented.

An MCP server that connects an agent to your Beamtrace AI visibility data. It exposes tools to analyze your score, explain a shift, see where a competitor is ahead, and pull the fix behind a visibility gap. Ready to plug

Explore GitHub Actions job performance, compute costs and failures with Runzumi’s remote MCP server. Connect securely with OAuth and query the workspaces and repositories you can access.
Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.
Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.
The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.
评论