Nerf Watch is an MCP server published by dev.tokenusage, hosted at tokenusage.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including get_nerfwatch_scores, get_nerfwatch_history.
Daily Nerf Watch scores for Claude and GPT models on one private, code-graded suite. Read-only.
202 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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
No parameters.
{
"name": "get_nerfwatch_scores",
"title": "Nerf Watch scores",
"description": "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",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"source",
"generatedAt",
"dataUpdatedAt",
"baselineDays",
"minBaselineRuns",
"flatPoints",
"models"
],
"properties": {
"models": {
"type": "array",
"items": {
"type": "object",
"required": [
"model",
"name",
"provider",
"latest",
"previous",
"change",
"baseline",
"baselineRuns",
"changeVsBaseline",
"trend"
],
"properties": {
"name": {
"type": "string",
"description": "The model's published display name."
},
"model": {
"type": "string",
"description": "The model id used by get_nerfwatch_history."
},
"trend": {
"enum": [
"down",
"flat",
"up",
null
],
"type": [
"string",
"null"
],
"description": "Direction versus baseline: down below -flatPoints, up above flatPoints, flat otherwise; null without a baseline."
},
"change": {
"type": [
"number",
"null"
],
"maximum": 100,
"minimum": -100,
"description": "Latest minus previous in points, rounded to two decimals; null without both runs on the same suite version."
},
"latest": {
"type": [
"object",
"null"
],
"required": [
"day",
"score",
"suiteVersion"
],
"properties": {
"day": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The run's UTC day, YYYY-MM-DD."
},
"score": {
"type": "number",
"maximum": 100,
"minimum": 0,
"description": "The suite percentage, rounded to two decimals."
},
"suiteVersion": {
"type": "string",
"description": "The suite version; score comparisons are within one version."
}
},
"description": "The newest retained run, or null.",
"additionalProperties": true
},
"baseline": {
"type": [
"number",
"null"
],
"maximum": 100,
"minimum": 0,
"description": "The mean same-suite score in the baseline window, rounded to two decimals; null with fewer than minBaselineRuns."
},
"previous": {
"type": [
"object",
"null"
],
"required": [
"day",
"score",
"suiteVersion"
],
"properties": {
"day": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The run's UTC day, YYYY-MM-DD."
},
"score": {
"type": "number",
"maximum": 100,
"minimum": 0,
"description": "The suite percentage, rounded to two decimals."
},
"suiteVersion": {
"type": "string",
"description": "The suite version; score comparisons are within one version."
}
},
"description": "The retained run before the latest, whatever its day or suite version, or null.",
"additionalProperties": true
},
"provider": {
"type": "string",
"description": "The model's published provider name."
},
"baselineRuns": {
"type": "integer",
"minimum": 0,
"description": "The number of same-suite runs in the baseline window, including when too few for a baseline."
},
"changeVsBaseline": {
"type": [
"number",
"null"
],
"maximum": 100,
"minimum": -100,
"description": "Latest minus baseline in points, rounded to two decimals; null without a baseline."
}
},
"additionalProperties": true
},
"maxItems": 100,
"description": "Models in source order: provider, name and model id; empty before the first run."
},
"source": {
"enum": [
"https://tokenusage.dev/nerfwatch"
],
"type": "string",
"description": "The fixed credit URL, https://tokenusage.dev/nerfwatch. Stable public Nerf Watch scores, changes, histories and metadata are licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Credit tokenusage.dev, link this URL and the licence, and indicate changes in a reasonable manner for the medium. The credit link may carry rel=\"nofollow\". Retain supplied attribution and licence information when redistributing the data."
},
"flatPoints": {
"type": "number",
"minimum": 0,
"description": "An absolute change versus baseline at or below this returned setting is flat."
},
"generatedAt": {
"type": "string",
"description": "When the cached data was read, ISO 8601 UTC; the cache TTL is 300 seconds from read start."
},
"baselineDays": {
"type": "integer",
"minimum": 1,
"description": "The UTC-day window before each latest run used for its baseline; this is the returned setting, not a fixed client assumption."
},
"dataUpdatedAt": {
"type": [
"string",
"null"
],
"description": "When the newest retained run was stored, ISO 8601 UTC; null without runs. This is distinct from response generation time."
},
"minBaselineRuns": {
"type": "integer",
"minimum": 1,
"description": "The minimum number of same-suite runs needed for a baseline; this is the returned setting."
}
},
"additionalProperties": true
},
"annotations": {
"title": "Nerf Watch scores",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
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
| Parameter | Type | Description |
|---|---|---|
| model * | string | A model id from get_nerfwatch_scores: 1 to 64 lowercase letters, digits, dots, underscores or hyphens, starting with a letter or digit. |
{
"name": "get_nerfwatch_history",
"title": "Nerf Watch history",
"description": "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",
"inputSchema": {
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9._-]{0,63}$",
"description": "A model id from get_nerfwatch_scores: 1 to 64 lowercase letters, digits, dots, underscores or hyphens, starting with a letter or digit."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"source",
"generatedAt",
"dataUpdatedAt",
"historyDays",
"model",
"name",
"provider",
"history"
],
"properties": {
"name": {
"type": "string",
"description": "The selected model's published display name."
},
"model": {
"type": "string",
"description": "The selected model id."
},
"source": {
"enum": [
"https://tokenusage.dev/nerfwatch"
],
"type": "string",
"description": "The fixed credit URL, https://tokenusage.dev/nerfwatch. Stable public Nerf Watch scores, changes, histories and metadata are licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Credit tokenusage.dev, link this URL and the licence, and indicate changes in a reasonable manner for the medium. The credit link may carry rel=\"nofollow\". Retain supplied attribution and licence information when redistributing the data."
},
"history": {
"type": "array",
"items": {
"type": "object",
"required": [
"day",
"score",
"suiteVersion"
],
"properties": {
"day": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The run's UTC day, YYYY-MM-DD."
},
"score": {
"type": "number",
"maximum": 100,
"minimum": 0,
"description": "The suite percentage, rounded to two decimals."
},
"suiteVersion": {
"type": "string",
"description": "The suite version; score comparisons are within one version."
}
},
"additionalProperties": true
},
"description": "Retained points, oldest first, including older suite versions; days without a run are missing, not zero."
},
"provider": {
"type": "string",
"description": "The selected model's published provider name."
},
"generatedAt": {
"type": "string",
"description": "When the cached data was read, ISO 8601 UTC; the cache TTL is 300 seconds from read start."
},
"historyDays": {
"type": "integer",
"minimum": 1,
"description": "The returned retention bound per model; clients read this setting rather than assuming 366."
},
"dataUpdatedAt": {
"type": [
"string",
"null"
],
"description": "When the newest retained run across the dataset was stored, ISO 8601 UTC; null without runs. This is dataset metadata, not a timestamp for this model alone."
}
},
"additionalProperties": true
},
"annotations": {
"title": "Nerf Watch history",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read-only Nerf Watch data from tokenusage.dev. get_nerfwatch_scores returns the latest public model scores, previous runs, changes and baselines. get_nerfwatch_history returns one model's retained public score history, oldest first. Model ids are available from get_nerfwatch_scores. Both tools share one 300-second read cache in each server instance. Missing days are missing, not zero. 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. Runs are noisy, and a provider's defaults, the endpoint or the runner itself can change.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.