Nerf Watch

dev.tokenusagePublished by tokenusage.devOfficial publisherv1.0.0Updated Nov 5, 2026

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

The publisher's own server: Codex Reset Tracker

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Read-only remote MCP server exposing public Nerf Watch scores and score history for Claude and GPT models on one code-graded suite.

What you can do
  • List latest public scores for up to 100 models, ordered by provider, name and model id, with previous runs, changes, baselines and trends
  • Fetch one model's retained score history, oldest first, with each point's suite version
  • Compare scores and changes within a single suite version, with values rounded to two decimals
When to use it
Useful when you want an assistant to look up or discuss how Claude and GPT models score on this particular private suite, or to trace a model's score over time, without any sign-in.
Requirements
A remote Streamable HTTP endpoint; no API key, account or sign-in is needed. Clients that accept the HTTP mcpServers format can add it directly.
Before you install
Scores are noisy and a lower score is not proof that a provider changed a model; defaults, endpoints or the runner can change. Missing days are missing, not zero. Poll no faster than every five minutes, and show the data credit when sharing results with others. Unofficial and not affiliated with OpenAI or Anthropic.

Installation

In SourceWeft

  1. Open Nerf Watch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.tokenusage%2Fnerfwatch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "nerf-watch": {
      "type": "http",
      "url": "https://tokenusage.dev/mcp/nerfwatch"
    }
  }
}

README

Nerf Watch MCP server

A hosted, read-only MCP server for the public scores and history behind Nerf Watch.

A lower score is a lower score on this suite, not proof that a provider changed a model. Runs are noisy, and a provider's defaults, the endpoint or the runner itself can change. Data: tokenusage.dev linked to https://tokenusage.dev/nerfwatch.

  • Endpoint: https://tokenusage.dev/mcp/nerfwatch (Streamable HTTP)
  • No API key, account or sign-in
  • Read-only public score data
  • Both tools share one 300-second read cache per server instance

This directory contains client documentation and Registry metadata. The hosted implementation source is not in this repository.

Tools

ToolArgumentsResult
get_nerfwatch_scoresnoneLatest public scores, previous runs, changes, baselines and trends; model ids are included.
get_nerfwatch_historyrequired model id from get_nerfwatch_scoresThat model's retained history, oldest first, with each point's suite version.

Missing days are missing, not zero. Scores and changes are rounded to two decimals. Comparisons are within one suite version. Retention and baseline settings come from the responses. Evidence answers, grader check lines and test questions are not returned.

Install

Claude Code:

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

Codex:

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

For Claude Code project scope, add this to .mcp.json. Other clients that accept this HTTP mcpServers format can use the same entry:

json
{  "mcpServers": {    "nerfwatch": {      "type": "http",      "url": "https://tokenusage.dev/mcp/nerfwatch"    }  }}

Discovery

The separate Codex reset server remains at https://tokenusage.dev/mcp.

Credit and terms

When showing this data to other people, show Data: tokenusage.dev linked to https://tokenusage.dev/nerfwatch on the same screen or in the same message. Personal use needs no visible credit. Relays retain the source URL and pass on this credit condition.

Please poll no faster than every five minutes and retain the score qualification above.

Terms: https://tokenusage.dev/terms
Privacy: https://tokenusage.dev/privacy
Questions and corrections: https://tokenusage.dev/contact

Unofficial; not affiliated with OpenAI or Anthropic.

Source: nerfwatch/README.md at commit ea14bd8

Tools

2

get_nerfwatch_scores

Nerf Watch 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 are available through get_nerfwatch_history. Scores and changes are rounded to two decimals; comparisons are within one suite version. A lower score is a lower score on this suite, not proof that a provider changed a model. Unofficial, not affiliated with OpenAI or Anthropic. Source: https://tokenusage.dev/nerfwatch

Takes no parameters.

get_nerfwatch_history

Nerf Watch 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_nerfwatch_scores. Missing days are missing, not zero; comparisons are within one suite version. A lower score is a lower score on this suite, not proof that a provider changed a model. Unofficial, not affiliated with OpenAI or Anthropic. Source: https://tokenusage.dev/nerfwatch

Parametersmodelrequired

Version history

1
  1. v1.0.0LatestOct 21, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Tokenusage integrations

Codex Reset Tracker

dev.tokenusageOfficial publisher

Hosted, read-only MCP server that lets an assistant look up announced OpenAI Codex usage-limit resets from one public X account.

Streamable HTTPWeb executable
Web Search & Scraping2 toolsNov 5, 2026