MCP.so
Sign In

Agent Analytics

@Agent-Analytics

Repository

About Agent Analytics

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

#analytics#tracking#experiments#ab-testing#funnel#retention#mcp

Basic information

Category

AI & Agents

Transports

stdio

Publisher

Agent-Analytics

Submitted by

Danny Shmueli

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agent-analytics": {
      "url": "https://mcp.agentanalytics.sh/mcp"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Agent Analytics?

Agent Analytics is an open-source, API-first analytics tool designed for AI agents. It enables agents to track performance across multiple projects, run A/B experiments, analyze funnels, and report results directly to the user. It works with Claude Code, Cursor, Windsurf, Codex, and any agent that communicates via HTTP or MCP, and requires no dashboard.

How to use Agent Analytics?

—

Key features of Agent Analytics

  • Tracks what’s working across multiple projects
  • Runs A/B experiments
  • Analyzes user funnels
  • Reports results back to your agent
  • Open source and API-first
  • No dashboard required

Use cases of Agent Analytics

  • AI agents monitoring performance across different projects
  • Automating A/B tests for agent-driven workflows
  • Analyzing funnel behavior from agent interactions
  • Receiving automated analytics reports without a UI

FAQ from Agent Analytics

Which agents are compatible with Agent Analytics?

Claude Code, Cursor, Windsurf, Codex, and any agent that speaks HTTP or MCP.

Is Agent Analytics open source?

Yes, it is open source.

Does Agent Analytics require a dashboard?

No, it is designed to be dashboard-free and agent-friendly.

What can my agent do with Agent Analytics?

Your agent can track performance, run A/B experiments, analyze funnels, and report back to you.

How does my agent communicate with Agent Analytics?

It communicates via HTTP or the MCP (Model Context Protocol).

Comments

More AI & Agents MCP servers

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K