Nerf Watch MCP Server

by tokenusage Your server? Claim it

answering

Nerf Watch is answering right now. Last checked 11 min ago. It exposes 2 tools. Last commit 22 Oct 2026.

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

Uptime history 4 days of history

4 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

253 ms

Response time

average over 24h

Stars

last commit 22 Oct 2026

Nothing serious here today

Today is the operative word: we check Nerf Watch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://tokenusage.dev/mcp/nerfwatch

~/.codex/config.toml

[mcp_servers.nerfwatch]
url = "https://tokenusage.dev/mcp/nerfwatch"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

nerfwatch

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_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

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 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

Endpoints

URL	Transport	State	Latency	Checked
https://tokenusage.dev/mcp/nerfwatch	streamable-http	answering	249 ms	11 min ago

Alternatives to Nerf Watch

same job, measured the same way

LLMemory

by meir-may

Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only

answering

Hermes Prime

by hermes-labs-ai

Read-only stdio MCP server for a versioned convention card in Claude Code.

123 installs/wk local only

AiPayGent — Claude AI Tools

by djautomd-lab

Claude-powered AI tools: research, write, code, analyze, translate, debate, pitch, score, and more.

121 installs/wk answering

Harness

by autonomous-harness

Start Claude Code and Codex agents the person can watch, wait for them and read their answers.

31 installs/wk local only

Renor

by patrickpassosb

Private memory for AI agents: save and recall facts across Claude Code, Codex, Cursor and ChatGPT.

answering

Ask Claude

by lykhoyda

Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions

138 installs/wk local only

Formy

by co-formy

Read your Formy forms and responses over OAuth. For Claude, ChatGPT, Cursor and VS Code.

answering

Sigistry Plugin & Skill Catalog

by sigistry

Search verified Claude Code plugins and skills; fetch portable SKILL.md sources. Read-only.

9 tools answering

Nerf Watch — questions

Answers built from our own checks of this server.

What can Nerf Watch do?

It exposes 2 tools, read directly from the server on our last check. Among them: get_nerfwatch_history, get_nerfwatch_scores. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Nerf Watch working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 253 ms. The bar chart above shows every period we have measured.

How do I connect Nerf Watch?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Nerf Watch need an API key?

No. Nerf Watch completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Nerf Watch?

It answers our handshake in 253 ms on average, which is faster than 66% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Nerf Watch open source?

The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at tokenusage.dev, which runs on its operator's own terms.