SigRank — Token Efficiency Leaderboard MCP Server

Operator leaderboard measuring users, not models — 20 tools, TUI, signed submit, privacy-first.

Local serverstdioGo

What is the SigRank — Token Efficiency Leaderboard MCP server?

SigRank — Token Efficiency Leaderboard MCP server exists for a simple reason — assistants are far more useful when they can act on SigRank — Token Efficiency Leaderboard directly instead of describing what you should do. Operator leaderboard measuring users, not models — 20 tools, TUI, signed submit, privacy-first.

What you get

That's it. sigrank reads your local AI session logs on-device, derives your token cascade (Υ Yield, Leverage, Velocity, 10xDEV), and publishes to signalaf.com. No paste, no transcript content — only the four token counts leave your machine.

What the assistant can call

Once SigRank — Token Efficiency Leaderboard is connected, these are the calls the assistant has available:

  • rank_windows — {platform?, window?}
  • watch_tokenpull — {platform?, interval_s?}
  • submit_verified — {window?, platform?, dry_run?}
  • enroll — {code, device_label?}
  • diagnose_cascade — {text?}
  • simulate_change — {text?, changes}
  • suggest_improvements — {text?}
  • self_improve — {text?}

Setting it up

sigrank on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. SigRank — Token Efficiency Leaderboard's toolset — rank_windows, watch_tokenpull, submit_verified and 5 more — is a fair guide to whether it matches your workflow. It is maintained by SunrisesIllNeverSee; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the sigrank — token efficiency leaderboard mcp server does with a few real requests.

Available tools

ToolWhat it does
rank_windows{platform?, window?}
watch_tokenpull{platform?, interval_s?}
submit_verified{window?, platform?, dry_run?}
enroll{code, device_label?}
diagnose_cascade{text?}
simulate_change{text?, changes}
suggest_improvements{text?}
self_improve{text?}

How to install the SigRank — Token Efficiency Leaderboard MCP server

Or if installed globally:

```json
{
  "mcpServers": {
    "sigrank": {
      "command": "sigrank"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use SigRank — Token Efficiency Leaderboard to rank windows.
  • Use SigRank — Token Efficiency Leaderboard to watch tokenpull.
  • Use SigRank — Token Efficiency Leaderboard to submit verified.

Frequently asked questions

It connects SigRank — Token Efficiency Leaderboard to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (rank_windows, watch_tokenpull, submit_verified, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with SigRank — Token Efficiency Leaderboard directly.