Koskamo

AI Footprint MCP

A remote Model Context Protocol server that calculates the water and energy footprint of AI usage. It provides tools to estimate chat use, compare water consumption, and estimate agent session footprints based on token counts, using a published methodology derived from vendor disclosures.

Visit PharmaTools.AI

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AI Footprint MCP logo, by PharmaTools.AIVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-10-26Operated by PharmaTools.AI
You need:Install one, or all six.AI Footprint is hosted: connect by URL, with nothing to install.
MCP endpoint (Streamable HTTP)
https://footprint.pharmatools.ai/mcp
Vendor documentation

What you can do with it

  • Estimate the energy and water footprint of AI chat prompts
  • Calculate the environmental cost of an agent session from token counts
  • Compare water usage across different AI workloads
  • Retrieve the methodology behind the sustainability calculations

Source and maintenance

Vendor evidenceRegistry 1.0.4MIT
mcp-registry: io.github.nickjlamb/ai-footprint@1.0.4Source repositoryProject website
Last repository push
Latest release
v1.0.4
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · repository · passed · metadata changed · unchanged
  • · repository · passed · metadata changed · updated
  • · registry · passed · metadata changed · Source metadata updated
  • · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http ai-footprint-mcp https://footprint.pharmatools.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add ai-footprint-mcp --url https://footprint.pharmatools.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-footprint-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "ai-footprint-mcp": {
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "ai-footprint-mcp": {
      "type": "streamableHttp",
      "url": "https://footprint.pharmatools.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-footprint-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "ai-footprint-mcp": {
      "type": "http",
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http ai-footprint-mcp https://footprint.pharmatools.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "ai-footprint-mcp": {
      "url": "https://footprint.pharmatools.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "ai-footprint-mcp": {
      "serverUrl": "https://footprint.pharmatools.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AI Footprint MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 3,794

Do you run AI Footprint MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing