Skip to main content

​
What is Surfa?

Surfa is the easiest way to understand what’s happening inside your AI agents and MCP servers. Stop debugging logs. Start asking questions. Instead of digging through scattered logs, just ask Claude:
  • “What’s my success rate this week?”
  • “Find all errors from yesterday”
  • “Which tools are slowest?”
Get instant answers powered by your real-time analytics.

​
The Problem

Building AI agents? You’re probably:
  • 🔍 Debugging scattered logs across multiple tools
  • 📊 Manually tracking metrics in spreadsheets
  • ❓ Guessing why tools fail without visibility
  • ⏰ Wasting hours investigating issues

​
The Solution

Add a few lines of code. Get instant insights. 
from surfa_ingest import SurfaClient

analytics = SurfaClient(ingest_key="sk_live_...")
analytics.track({
    "kind": "tool",
    "subtype": "call_completed",
    "tool_name": "search",
    "status": "success"
})
Then ask Claude: “Show me my analytics overview” → Get instant answers with real data.

​
How It Works

1

Instrument

Add the Surfa SDK to your MCP server (2 lines of code)
2

Track

Events are auto-captured in real-time to your dashboard
3

Query

Ask questions in natural language through Claude Desktop
4

Insights

Get AI-powered analysis, recommendations, and alerts

​
Quick Start

5-Minute Quickstart

Get Surfa running in 5 minutes with our step-by-step guide.

Claude Desktop Setup

Query your analytics with natural language through Claude.

​
Two Products

Surfa SDK

Track events from your MCP server. Auto-capture sessions, latency, errors, and runtime metadata.

Surfa MCP Server

Query your analytics with natural language through Claude Desktop. No dashboards needed.

​
Why Surfa?

No complex logging infrastructure. No data pipelines. Just add the SDK and you’re done.
Built specifically for MCP patterns. Understands sessions, tools, and agent workflows out of the box.
Events appear in your dashboard instantly. No waiting for batch jobs or ETL.
Ask questions in natural language. Get insights and recommendations from AI that understands your data.

​
Perfect For

Product Managers

Track adoption, success rates, and user behavior without SQL.

Developers

Debug faster with session replay and error tracking.

DevOps Teams

Monitor performance, latency, and uptime in real-time.

​
Example Queries

See what you can ask Claude with the Surfa MCP Server: 
"Show me my analytics overview"
Response Format: All tools return JSON for easy parsing by AI agents: 
{
  "ok": true,
  "data": {
    "totalSessions": 150,
    "successRate": 85,
    "avgExecutionTime": 245,
    "activeSessions": 12
  }
}

​
Multi-Query Workflows

The PM Agent can chain queries together for complex analysis: Example workflow:
  1. Get analytics → sees low success rate (54%)
  2. Query events with status=error → finds “Database unavailable” errors
  3. Analyze patterns → identifies Feb 21-22 outage
  4. Provide recommendations → Add health checks, circuit breakers
All in seconds. No dashboards. No SQL.

​
Ready to Start?

Get Started Now

Follow our quickstart guide and be up and running in 5 minutes.

View on GitHub

Star us on GitHub and contribute to the project.

Join Community

Get help, share feedback, and connect with other users.