FaceabotCapability network for AI agents
AppConnect your agent
‹ Back

Catalog › dev.tokenusage/nerfwatch

Is Nerf Watch reliable?

Reliable (measured) Yes. Faceabot measured Nerf Watch 6 times: 100% of checks succeeded, including the last 6 in a row (last check 2026-10-24 04:55 UTC). It also does the job: its real read-only task worked 6 of 6 times.

Last check: 2026-10-24 04:55 UTC · answered in 3090 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website
Connect your agent
{
  "mcpServers": {
    "nerfwatch": {
      "url": "https://tokenusage.dev/mcp/nerfwatch"
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"dev.tokenusage/nerfwatch"} on https://faceabot.com/api/mcp.
Does it actually do the job?

Does the job (tested) — Faceabot asked get_nerfwatch_scores to do a small read-only task 6 time(s): 6 returned a real result, the last 6 in a row. Last result: ok in 1957 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.
Faceabot measurements
WhenAnswersReal taskLatency
2026-10-24 04:55 UTC✅ ok✅ done3090 ms
2026-10-23 18:11 UTC✅ ok✅ done6987 ms
2026-10-23 07:47 UTC✅ ok✅ done5075 ms
2026-10-22 21:16 UTC✅ ok✅ done6240 ms
2026-10-22 10:01 UTC✅ ok✅ done6661 ms
2026-10-21 23:00 UTC✅ ok✅ done7040 ms
Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

Codex Reset Tracker Reliable (measured) · 100% over 44 checks Does the job (tested) · 44/44

Codex reset tracker: usage-limit reset announcements from @thsottiaux on X. Read-only, no key.

MCP endpoint : https://tokenusage.dev/mcp · website · measurements and details

Find tools similar to Nerf Watch →

Publisher of Nerf Watch?

Show your measured reliability on your README or website:

Faceabot reliability badge for Nerf Watch

[![Measured by Faceabot](https://faceabot.com/badge/dev.tokenusage/nerfwatch.svg)](https://faceabot.com/tools/dev.tokenusage/nerfwatch)
Data in JSON: /api/catalog?id=dev.tokenusage/nerfwatch · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms