Turn your code assistant (Claude Code, Cursor, Claude Desktop, …) into the frontend for nullplatform. Deploy, move traffic, roll back, read logs and config — from the place you already work, aware of the repo you're in. Most actions take zero arguments inside a linked repo.

you    › deploy this
claude › Deploying #4312 on dev — waiting for instances
         Created release 1.4.2 from build #991 (main @ab12cd34)
         → Next: move traffic to 25%

What it does

• Deploy & release — ship the latest build, cut the release, walk traffic (canary → 100%), finalize or roll back.
• Observe — recent builds, logs, and golden-signal metrics per scope.
• Configure — environment variables & file parameters (secret values masked).
• "Is anything broken?" — an org-wide digest across all your apps, no app name needed.
• Interactive — on hosts that render MCP Apps (claude.ai, ChatGPT) you get live panels, a traffic slider, and log/metric views; terminals get clean markdown.

Installation

You need a nullplatform API key (create one in the dashboard, or run np login). It runs via npx — no install, no clone.

Claude Code

claude mcp add nullplatform -e NP_API_KEY=<your-key> -- npx -y @nullplatform/mcp

Claude Desktop — Settings → Developer → Edit Config, then fully restart:

{
  "mcpServers": {
    "nullplatform": {
      "command": "npx",
      "args": ["-y", "@nullplatform/mcp"],
      "env": { "NP_API_KEY": "<your-key>" }
    }
  }
}

Cursor / Windsurf / others — same shape in their mcp.json (command: "npx", args: ["-y", "@nullplatform/mcp"], env.NP_API_KEY).

Usage

Open your assistant in a repo linked to a nullplatform application and just ask:

• "what's the status?" · "is anything broken?"
• "deploy this to dev"
• "move traffic to 50%" · "finalize" · "roll me back"
• "show logs" · "show metrics"
• "set DATABASE_URL as a secret"

Most tools infer the application from your git remote, so you rarely pass arguments. There are also three slash-command prompts: /ship, /setup, /rollback.

Self-hosting (multi-user)

Run it as a shared HTTP server where every caller brings their own key:

npx -y @nullplatform/mcp --http 8080   # → http://host:8080/mcp

The server holds no credentials — each request authenticates with the caller's own nullplatform key, so platform RBAC applies per user. Run it behind a TLS-terminating reverse proxy on a trusted network.

Debug logging

Off by default. Set NP_LOG_LEVEL (debug/info/warn/error) to turn on structured logs of every platform API call (method, path, status, latency) and key tool internals. Logs go to stderr (never stdout, which carries the stdio protocol), or to a file with NP_LOG_FILE. Credentials are redacted.

"env": { "NP_API_KEY": "<your-key>", "NP_LOG_LEVEL": "debug", "NP_LOG_FILE": "/tmp/np-mcp.log" }

Documentation

Full tool reference, the multi-user security model, design rationale, and the development guide: docs/ARCHITECTURE.md.

License

MIT