Costlens — Ai Productivity Tracking

@Costlens

21 days ago

Track AI productivity automatically via MCP. Measures sessions, commits, PRs, cost per deliverable, and generates ROI reports for engineering leaders. Zero latency — all tracking is async.

Overview Tools Comments

Overview

CostLens MCP Server

AI productivity tracking for coding agents. Measures what AI actually ships.

Features

Automatic session tracking (start, end, heartbeat)
Event logging (commits, PRs, deploys, file edits)
Cost tracking per session and per deliverable
GitHub PR metrics (review rounds, time to merge)
Productivity reports with ROI calculation
Zero latency — all tracking is async, never blocks your workflow

Quick Start

npx @costlens/mcp-server setup

One command. Browser opens, authenticates, auto-configures your agent. 30 seconds.

Tools

start_session — Begin tracking a coding session
end_session — End session with outcome + artifacts
log_event — Log commits, PRs, deploys
get_productivity_summary — Sessions, cost, output for a period
get_spend_summary — Daily/weekly/monthly AI spend
get_github_metrics — PRs merged, review rounds, cost per PR
costlens_suggest_model — Get cost-optimized model suggestion

Server Config

{
  "mcpServers": {
    "costlens": {
      "command": "npx",
      "args": [
        "-y",
        "@costlens/mcp-server"
      ],
      "env": {
        "COSTLENS_MCP_KEY": "<YOUR_KEY>"
      }
    }
  }
}

Build with ShipAny.