dev.tokenusage/nerfwatch

up checked 2026-11-10T22:37:57.256Z

Unclaimed · Unverified

Publisher-provided title

Nerf Watch

Publisher-provided description

Daily Nerf Watch scores for Claude and GPT models on one private, code-graded suite. Read-only.

Summary by lookupd

Lets an agent read daily scores, score history and changes for Claude and GPT models from a read-only benchmark suite.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http nerfwatch https://tokenusage.dev/mcp/nerfwatch

Codex, remote (streamable-http)

codex mcp add nerfwatch --url https://tokenusage.dev/mcp/nerfwatch

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "nerfwatch": {
      "url": "https://tokenusage.dev/mcp/nerfwatch"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

get_nerfwatch_scores Latest public Nerf Watch scores, previous runs, changes and baselines for at most 100 models, ordered by provider, name and model id. No arguments. Histories ar
get_nerfwatch_history Retained public Nerf Watch score history for one model, oldest first, including each point's suite version. The required model id is available from get_nerfwatc

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/dev.tokenusage/nerfwatch.svg)](https://lookupd.com/servers/dev.tokenusage/nerfwatch)