# AI Footprint

> AI Footprint is an open-source MCP server for ai models and llm tooling. Estimate the water and energy a chat prompt or a whole agent session uses. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API, Web
- **Website:** https://www.pharmatools.ai/mcp
- **Repository:** https://github.com/nickjlamb/ai-footprint
- **MCP Registry name:** io.github.nickjlamb/ai-footprint
- **Categories:** AI models and LLM tooling, analytics and data
- **Listing updated:** 2026-11-14

## About

The server exists because published per-prompt water figures range from about 0.3 mL to 50 mL, a spread explained by when it was measured, where the boundary is drawn and what workload is counted. So every answer states its boundary, assumptions and methodology version, letting you cite or challenge the number.

The tools are plain arithmetic over a published, versioned methodology, with no model in the loop, so the same input always yields the same answer. A session estimator takes input, cached and output token counts for an agent run and gives a central estimate with a 0.3 to 3 times range, converted into an equivalent number of chat prompts.

It is part of a family of open-source MCP servers from PharmaTools.AI. The hosted endpoint is read-only and needs no key, and the same functions are also available as plain GET endpoints. Model training is excluded from the figures.

## Features

- **Prompt footprint:** Energy and water per prompt, per day and in total, with everyday equivalents.
- **Session estimate:** Turns token counts into a footprint range for an agent session.
- **Water comparisons:** Relates a volume to teaspoons, bottles and shower time.
- **Methodology:** Returns sources, limitations and a citation line.
- **Deterministic:** No model is involved; results are repeatable.
- **JSON API:** The same calculations are exposed over GET endpoints.

## Good for

- Quantify a year of daily chat use
- Estimate the footprint of a long coding-agent session
- Cite a sourced figure in a sustainability report
- Explain why published estimates differ

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http ai-footprint https://footprint.pharmatools.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://footprint.pharmatools.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "ai-footprint": {
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "ai-footprint": {
      "type": "http",
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "ai-footprint": {
      "serverUrl": "https://footprint.pharmatools.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "ai-footprint": {
      "type": "http",
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}
```

## Tools

- `estimate_ai_footprint`: Estimates energy and water for prompts over a period.
- `estimate_session_footprint`: Estimates the footprint of an agent session from token counts.
- `compare_water_use`: Puts a water volume into everyday terms.
- `get_methodology`: Returns the methodology, sources and limitations.

## FAQ

### Do I need a key?

No. The hosted endpoint is read-only with no key, install or account.

### Which boundaries are supported?

Onsite and comprehensive, each noted in the output.

### Does it include training?

No, model training is excluded.

### Are the numbers stable?

Yes. Same input gives the same answer, and results carry a methodology version.

### Is AI Footprint free?

Yes. AI Footprint is open source, so you can use and self-host it for free.

### How do I add AI Footprint to Claude Code?

Run this command in your terminal: claude mcp add --transport http ai-footprint https://footprint.pharmatools.ai/mcp

### What are the best alternatives to AI Footprint?

The closest alternatives to AI Footprint are Agent-Native Analytics, Claude Code Ultimate Guide, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP and World Monitor.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/ai-footprint
