Connect Cursor

Cursor talks to Pileless through the same MCP server as Claude Code and Codex — you just register it in Cursor's MCP config. About two minutes.

1. Get your Pileless API key

Grab a workspace API key (ak_…) from Pileless → Settings → API keys — create one and copy it (it's shown only once).

Prefer a file over an env var? Put the key in ~/.pileless/config.json as {"api_key": "ak_…"} — the MCP server reads it automatically.

2. Register the MCP server in Cursor

Cursor reads MCP servers from ~/.cursor/mcp.json (global, all projects) or .cursor/mcp.json in a project folder. Add a Pileless entry:

{
  "mcpServers": {
    "pileless": {
      "command": "npx",
      "args": ["-y", "@pileless/mcp"],
      "env": { "PILELESS_API_KEY": "ak_…" }
    }
  }
}

You can also add it from the UI: Cursor → Settings → MCP → Add new MCP server, then paste the same command, args, and env.

3. Verify

Open Settings → MCP — pileless should show a green dot and its tools listed. In Agent mode, ask it: "create a test pile to approve and send me the link." A pile should appear in your inbox.

If the server shows red, copy the command + args from your config and run them in a terminal to see the error — a missing or wrong PILELESS_API_KEY is the usual cause.

4. Use it

Add the piling rule to your Cursor agent rules (Settings → Rules, or a .cursor/rules file) so it routes decisions to you instead of guessing:

When you're about to send/post/publish/commit, or you have 2+ options
for me to choose from, create a Pileless pile and wait for my decision.

Now Cursor's Agent can run long edits and queue every human call — approve, pick-one, annotate — into one inbox you clear later.

Next: bring your own cloud →