# Nerf Watch (remote · tokenusage.dev)

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

- Trust score: 74/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `tokenusage.dev`: 74/100 (this document), [markdown](https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch.md), [page](https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch)

## Channel facts

- Endpoint: `https://tokenusage.dev/mcp/nerfwatch`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 409 tokens (~204/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Nerf Watch MCP server?

Nerf Watch is a hosted endpoint at https://tokenusage.dev/mcp/nerfwatch, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

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

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-tokenusage-nerfwatch": {
      "type": "remote",
      "url": "https://tokenusage.dev/mcp/nerfwatch",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-tokenusage-nerfwatch --url 'https://tokenusage.dev/mcp/nerfwatch' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-tokenusage-nerfwatch:
    url: "https://tokenusage.dev/mcp/nerfwatch"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-tokenusage-nerfwatch": {
      "Transport": "http",
      "Url": "https://tokenusage.dev/mcp/nerfwatch"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-tokenusage-nerfwatch -t streamable-http -u 'https://tokenusage.dev/mcp/nerfwatch'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 73, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-21 (score 73)

First indexed and scored.

## MCP tools (2)

### `get_nerfwatch_scores` (~117 tokens)

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

Output parameters:

- `baselineDays` (integer): The UTC-day window before each latest run used for its baseline; this is the returned setting, not a fixed client assumption.
- `dataUpdatedAt` (string|null): When the newest retained run was stored, ISO 8601 UTC; null without runs. This is distinct from response generation time.
- `flatPoints` (number): An absolute change versus baseline at or below this returned setting is flat.
- `generatedAt` (string): When the cached data was read, ISO 8601 UTC; the cache TTL is 300 seconds from read start.
- `minBaselineRuns` (integer): The minimum number of same-suite runs needed for a baseline; this is the returned setting.
- `models` (array): Models in source order: provider, name and model id; empty before the first run.
- `source` (string): The fixed credit URL, https://tokenusage.dev/nerfwatch. When showing the data to other people, show Data: tokenusage.dev linked to this URL on the same screen or in the same message. Personal use nee…

### `get_nerfwatch_history` (~149 tokens)

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

Input parameters:

- `model` (string, required): A model id from get_nerfwatch_scores: 1 to 64 lowercase letters, digits, dots, underscores or hyphens, starting with a letter or digit.

Output parameters:

- `dataUpdatedAt` (string|null): 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.
- `generatedAt` (string): When the cached data was read, ISO 8601 UTC; the cache TTL is 300 seconds from read start.
- `history` (array): Retained points, oldest first, including older suite versions; days without a run are missing, not zero.
- `historyDays` (integer): The returned retention bound per model; clients read this setting rather than assuming 366.
- `model` (string): The selected model id.
- `name` (string): The selected model's published display name.
- `provider` (string): The selected model's published provider name.
- `source` (string): The fixed credit URL, https://tokenusage.dev/nerfwatch. When showing the data to other people, show Data: tokenusage.dev linked to this URL on the same screen or in the same message. Personal use nee…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch#diagnostics

## Score history

- 2026-10-23: 74
- 2026-10-22: 73
- 2026-10-21: 73

## Common questions

### What is the Nerf Watch MCP server?

Nerf Watch is an MCP server listed in the public MCP registry as dev.tokenusage/nerfwatch. Daily Nerf Watch scores for Claude and GPT models on one private, code-graded suite. Read-only. This page covers its hosted endpoint (https://tokenusage.dev/mcp/nerfwatch).

### Is the Nerf Watch MCP server safe to use?

Nerf Watch scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Nerf Watch MCP server expose?

Nerf Watch exposes 2 tools: get_nerfwatch_scores, get_nerfwatch_history. Their descriptions and schemas cost roughly 266 tokens of context every time the server is loaded.

### Does the Nerf Watch MCP server require authentication?

No. We connected to Nerf Watch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Nerf Watch MCP server still maintained?

Nerf Watch is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://tokenusage.dev/mcp/nerfwatch
- Repository: https://github.com/stdcmms-lang/tokenusage-codex-mcp
- Website: https://tokenusage.dev/nerfwatch
- Changelog RSS feed: https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch.json
- HTML version of this page: https://verifymcp.io/servers/dev-tokenusage-nerfwatch/mcp-nerfwatch