About Nerf Watch
Nerf Watch is a hosted, read-only MCP server for public Claude and GPT model scores on a code-graded suite, plus their history. Its results describe performance on that suite and do not establish that a provider changed a model.
Key features
- 01Retrieve latest public scores and prior runs
- 02View score changes, baselines, and trends
- 03Query retained history by model ID
- 04Include suite versions in historical points
Use cases
- 01Check recent model scores on the suite
- 02Track one model's results across runs
MCP support
It provides read-only score and history tools to MCP clients over Streamable HTTP, with no API key or sign-in required.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tokenusage.dev/mcp/nerfwatchclaude mcp add --transport http dev-tokenusage-nerfwatch https://tokenusage.dev/mcp/nerfwatch{"mcpServers":{"dev-tokenusage-nerfwatch":{"type":"http","url":"https://tokenusage.dev/mcp/nerfwatch"}}}Open in Cursor{"servers":{"dev-tokenusage-nerfwatch":{"type":"http","url":"https://tokenusage.dev/mcp/nerfwatch"}}}Open in VS Code{"mcpServers":{"dev-tokenusage-nerfwatch":{"type":"http","url":"https://tokenusage.dev/mcp/nerfwatch"}}}{"mcpServers":{"dev-tokenusage-nerfwatch":{"serverUrl":"https://tokenusage.dev/mcp/nerfwatch"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMENerf 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
| Tool | Arguments | Result |
|---|---|---|
get_nerfwatch_scores | none | Latest public scores, previous runs, changes, baselines and trends; model ids are included. |
get_nerfwatch_history | required model id from get_nerfwatch_scores | That 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:
claude mcp add --transport http nerfwatch https://tokenusage.dev/mcp/nerfwatch
Codex:
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:
{
"mcpServers": {
"nerfwatch": {
"type": "http",
"url": "https://tokenusage.dev/mcp/nerfwatch"
}
}
}
Discovery
- Registry name:
dev.tokenusage/nerfwatch - Manifest: server.json
- Server card: https://tokenusage.dev/mcp/nerfwatch/server-card
- AI catalog: https://tokenusage.dev/.well-known/ai-catalog.json
- Fields, caching and access: https://tokenusage.dev/developers
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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.