👁 Mata — see your AI footprint

An MCP server that estimates the environmental footprint of your AI use — energy (kWh), miles driven in a gas car, water used for cooling, and CO₂ — plus a prompt-efficiency coach. It works with any AI client (Claude, Codex, others) because it measures token usage, not a specific vendor.

Mata is Tagalog for eye — in the spirit of seeing what's there.

The impact math is a TypeScript port of the EcoLogits life-cycle methodology (CC BY-SA 4.0). See METHODOLOGY.md for sources and attribution.

What we're building (explained simply)

The problem: Every time you talk to an AI like Claude, a powerful computer in a big warehouse (a "data center") does the thinking. That computer burns electricity. Making electricity usually creates pollution (carbon), and the computer gets hot, so the data center uses water to cool it down. Most people have no idea how much — it's invisible.

Mata makes it visible. Like a fitness tracker for your AI use: it counts the AI's words and turns them into:

• ⚡ Energy used (in kWh, like your electric bill)

• 🚗 Miles driven in a gas car that would pollute the same amount

• 💧 Water used to cool the computers

• 🔤 Words in and out (tokens)

Bonus — a prompt coach. If you ask the AI to "make a thing" then correct it five times, that wasted energy. Mata scores how efficiently you set up your work (0–100) and gives tips to get more done in fewer prompts.

Why it's different: it doesn't care which AI you use — it watches the words, so it works across Claude, Codex, and more. Everything stays on your machine, and it stores word-counts, never your chats.

Related MCP server: TokenLens MCP

The tech stack (explained simply)

A kitchen that turns raw ingredients (AI word-counts) into a finished meal (the impact numbers):

Runs without AI (overhead ≈ 0)

A tool that measures AI's footprint shouldn't burn AI to do it. Mata's entire pipeline — capturing usage, doing the math, scoring efficiency, drawing the dashboard — is deterministic. Nothing in the data path calls an LLM.

Runtime dependencies are just @modelcontextprotocol/sdk, gpt-tokenizer, and zod — none of which make AI or network calls.

Run it with zero AI in the loop. The three standalone binaries need no LLM host:

ai-impact-tail        # watch Claude Code logs and record usage
ai-impact-proxy       # capture exact usage from API clients
ai-impact-dashboard   # render the HTML dashboard

One honest caveat: if you talk to Mata through an AI assistant ("show me my report"), that chat turn is the host's LLM call — Mata's own tools add nothing. Fittingly, Mata would measure that turn too. 🙂

Installation

Requires Node ≥ 22.5 (uses the built-in node:sqlite — no native build step).

git clone https://github.com/anchetadev/mata.git
cd mata
npm install
npm run build
npm test          # 36 tests

Add to an MCP host

Claude Desktop (claude_desktop_config.json) or Claude Code (.mcp.json / claude mcp add):

{
  "mcpServers": {
    "mata": { "command": "node", "args": ["/absolute/path/to/mata/dist/server.js"] }
  }
}

The same dist/server.js works in any MCP-compatible host (Cursor, Cline, etc.).

Optional collectors (run alongside)

node dist/tail-server.js       # watch Claude Code logs, record EXACT usage live
node dist/proxy-server.js      # local proxy: capture EXACT usage from API clients
node dist/dashboard-server.js  # write a static HTML dashboard file
node dist/serve-server.js      # live dashboard at http://localhost:8799 (auto-updates)

For the proxy, point a client at it:

ANTHROPIC_BASE_URL=http://localhost:8788   # Claude Code, Anthropic SDK
OPENAI_BASE_URL=http://localhost:8788/v1   # Codex, OpenAI SDK

Quick start

Already installed and built? Two commands get you from zero to seeing your footprint:

node dist/tail-server.js     # backfills your Claude Code history, then watches live
node dist/serve-server.js    # opens a live dashboard at http://localhost:8799

The first reads your existing ~/.claude logs (token counts only — never your messages) and keeps recording new activity. The second opens your browser to an always-current dashboard. That's ~90% of the value.

Prefer to drive it from your AI host? If you added Mata as an MCP server, just say:

• "Scan my Claude Code logs" → backfill your history

• "Serve my live dashboard" → get a live localhost URL

• "Show my AI impact this week" → a text report

• "How efficient were my last 5 sessions?" → prompt coaching

Want to capture non-Claude-Code tools too? Run the proxy and point a client at it:

node dist/proxy-server.js    # then set ANTHROPIC_BASE_URL / OPENAI_BASE_URL=http://localhost:8788

Stopping a server. tail, serve, and proxy run in the foreground — press Ctrl+C in their terminal to stop them cleanly. If you started one in the background, stop it by its port (8799 = dashboard, 8788 = proxy):

# Windows (PowerShell)
Get-Process -Id (Get-NetTCPConnection -LocalPort 8799).OwningProcess | Stop-Process

# macOS / Linux
kill $(lsof -ti:8799)

If you installed globally (npm link or npm i -g), use the bare commands instead — ai-impact-tail, ai-impact-serve, ai-impact-proxy.

Usage

Once connected, ask your host things like "estimate the impact of a 2000-token reply from claude-opus-4-5" or "show my AI impact report for this week."

Tools

Resource: impact://methodology — how the numbers are derived.

CLI binaries

How invasive is it?

Short answer: as little as possible, and entirely on your machine. Mata stores token counts and metadata — never the content of your messages — in a local SQLite file at ~/.ai-impact/usage.db. No telemetry, no network calls except the proxy forwarding to the provider you chose.

Each capture method is opt-in and differs in what it can see:

What it cannot see: the Claude desktop/web apps talk to Anthropic directly, so Mata can't passively read them — the web estimator only sees what you choose to hand it. The proxy only sees clients you explicitly repoint.

Every record is tagged exact or estimated, and estimates use a public BPE tokenizer as a stand-in (Claude's isn't public), so they carry ~±10% error.

Accuracy & honesty

These are order-of-magnitude estimates, good for "which of my habits cost the most" — not carbon accounting. Closed-model parameters are inferred; consumer surfaces are re-tokenized. The tool shows its assumptions in every result and ships full sources in METHODOLOGY.md.

License

Dual-licensed (see LICENSE and NOTICE):

• Original code (server, collectors, scorer, dashboard) — MIT.

• Impact engine + vendored data (ported from EcoLogits) — CC BY-SA 4.0 (attribution + share-alike).

Publishing guidance for your own fork: PUBLISHING.md.