io.github.agentwares/readiness-scorer
Readiness scorer — can an agent sign up to your SaaS?
Probe a signup URL you own and score whether an AI agent can sign up unaided.
alive probed 2026-10-05 · HTTP 200
3tools
749tokens in Claude Opus 5.5
785tokens in Claude Code
0.4 %of a 200k context window
443o200k_base estimate
149 msto initialize
58 msto list tools
- Endpoint
- https://agentwares-readiness.vercel.app/api/mcp (streamable-http)
- Host
- agentwares-readiness.vercel.app
- Protocol
- 2025-11-25
- Reports itself as
- readiness-scorer 0.1.2
- Capabilities
- logging, tools
- Instructions
- 253 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/agentwares/servers
- Website
- https://agentwares-readiness.vercel.app
- Registry
- active, updated 2026-09-12 · registry entry
- Reachable
- 5 of the last 5 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| readiness_request_scan | 174 | 39 % |
| readiness_get_verification_token | 145 | 33 % |
| readiness_get_scan | 124 | 28 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 00:31 | alive | 149 ms | 3 | 749 | 443 |
| 2026-10-04 10:03 | alive | 511 ms | 3 | 443 | |
| 2026-10-04 07:57 | alive | 432 ms | 3 | 443 | |
| 2026-10-03 20:36 | alive | 489 ms | 3 | 443 | |
| 2026-10-03 17:52 | alive | 351 ms | 3 | 443 |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.agentwares/readiness-scorer)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.