Analytics your AI agent can actually use. Your agent tracks what's working across multiple projects, runs A/B experiments, analyzes funnels, and reports back to you. Works with Claude Code, Cursor, Windsurf, Codex, and any agent that speaks HTTP or MCP. Open source, API-first, no dashboard required.
Server Config
{
"mcpServers": {
"agent-analytics": {
"url": "https://mcp.agentanalytics.sh/mcp"
}
}
}