Nerf Watch

dev.tokenusage由 tokenusage.dev 发布官方发布者v1.0.0更新于 Nov 5, 2026

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

发布方自己的服务：Codex Reset Tracker

已验证Streamable HTTP可网页运行数据与分析AI 与机器学习

概览

AI 生成的概览

只读的远程 MCP 服务器，提供 Claude 与 GPT 模型在同一套代码评分测试上的公开 Nerf Watch 分数与历史记录。

可以做什么
  • 按提供商、名称和模型 id 排序列出最多 100 个模型的最新公开分数，含上次运行、变化、基线与趋势
  • 获取单个模型保留的分数历史，按时间从旧到新，并附每个数据点的测试套件版本
  • 在同一套件版本内比较分数与变化，数值保留两位小数
适用场景
当你想让助手查询或讨论 Claude 与 GPT 模型在这套私有测试上的得分，或追踪某模型分数随时间的变化，且不希望登录时使用。
运行要求
需要远程 Streamable HTTP 端点；无需 API 密钥、账号或登录。支持 HTTP mcpServers 格式的客户端可直接添加。
安装前请注意
分数存在波动，分数较低并不能证明提供商更改了模型；默认设置、端点或运行器都可能变化。缺失的日期就是缺失，不是零。轮询间隔不要快于五分钟，向他人展示结果时需标注数据来源。非官方，与 OpenAI 或 Anthropic 无关联。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Nerf Watch，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/dev.tokenusage%2Fnerfwatch/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "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.

来源：nerfwatch/README.md，提交 ea14bd8

工具

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

无需输入参数。

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

输入参数model必填

版本历史

1
  1. v1.0.0最新Oct 21, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Tokenusage 集成

Codex Reset Tracker

dev.tokenusage官方发布者

托管式只读 MCP 服务器，让助手查询某个公开 X 账号发布的 OpenAI Codex 用量额度重置公告。

Streamable HTTP可网页运行
网页搜索与抓取2 个工具Nov 5, 2026