AI Agents
Model Context Protocol

DAMM inside Claude and Google Antigravity

The DAMM MCP server brings 4-pillar decision analysis straight into your AI assistant. Ask about a decision and get scores, a Health Score and a structured verdict — without leaving the chat.

Install in 1 minute API documentation

Setup

One standard, one command. Paste the config into your MCP client.

Claude Desktop

Add the block to your claude_desktop_config.json and restart Claude.

Claude Code

A single command from the terminal:

claude mcp add damm -- npx -y damm-decision-engine

Antigravity & other clients

Google Antigravity, Cursor, Windsurf and any MCP client use the same JSON config block.

MCP config (Claude Desktop, Antigravity, Cursor…)
{
  "mcpServers": {
    "damm": {
      "command": "npx",
      "args": ["-y", "damm-decision-engine"],
      "env": { "DAMM_API_KEY": "damm_sk_..." }
    }
  }
}

The env block is optional: omit DAMM_API_KEY for free mode. With the key, analysis runs on the DAMM AI engine.

Prefer self-hosting? Build the package (npm install && npm run build) and use "command": "node" with the absolute path to dist/index.js.

Free and Pro

Free — no key

  • Full DAMM method provided to the assistant
  • 4-pillar analysis run by your own LLM
  • Health Score and verdict structure
  • No account required

Pro — with API key

  • Verdict from the DAMM decision engine
  • Decisions saved to your account
  • EU AI Act (Art. 50) disclosure on every verdict
  • Entry in the AI decision registry (audit trail)

Frequently asked questions

What is an MCP server?

The Model Context Protocol (MCP) is an open standard that lets AI assistants use external tools. An MCP server exposes a capability — here, DAMM decision analysis — to any compatible client, such as Claude or Google Antigravity.

Does it work with Claude and Antigravity?

Yes. Being a standard, the same server runs on Claude Desktop, Claude Code, Google Antigravity, Cursor, Windsurf and any MCP client. Only where you paste the config differs.

Do I need a paid account?

Not for free mode: the server provides the DAMM method and lets your assistant apply it. Pro mode — which uses the DAMM AI engine, saves decisions and records them in the audit trail — requires an API key with an active plan.

What is the difference between free and pro?

In free mode your assistant runs the analysis following the DAMM structure (4 pillars, Health Score). In pro mode the request goes to the DAMM decision engine, which returns a scored verdict, an EU AI Act (Art. 50) disclosure and an immutable entry in the AI decision registry.

Bring DAMM into your assistant

Free to start. Move to the AI engine and audit trail with an API key.

Request an API key API documentation

Claude, Claude Code and Google Antigravity are products of their respective owners; the DAMM MCP server is an independent client that integrates via the Model Context Protocol. Pro-mode verdicts are generated by an AI system: human oversight is recommended before acting.