io.github.sattyamjjain/whycant
mcp-typescript server on vercel
Roast any AI agent idea from your IDE: verdict tier, readiness score, top risk, shareable URL.
alive probed 2026-10-05 · HTTP 200
4tools
886tokens in Claude Opus 5.5
918tokens in Claude Code
0.4 %of a 200k context window
535o200k_base estimate
1.2 sto initialize
145 msto list tools
- Endpoint
- https://whycantwehaveanagentforthis.com/api/mcp (streamable-http)
- Host
- whycantwehaveanagentforthis.com
- Protocol
- 2025-11-25
- Reports itself as
- mcp-typescript server on vercel 0.1.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/sattyamjjain/whycantwehaveanagentforthis
- Website
- https://whycantwehaveanagentforthis.com/mcp
- Registry
- active, updated 2026-07-05 · registry entry
- Reachable
- 6 of the last 6 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| roast_idea | 187 | 35 % |
| browse_explore | 159 | 30 % |
| get_verdict | 103 | 19 % |
| get_stats | 86 | 16 % |
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 16:28 | alive | 1.2 s | 4 | 886 | 535 |
| 2026-10-05 00:55 | alive | 333 ms | 4 | 535 | |
| 2026-10-04 10:07 | alive | 1.2 s | 4 | 535 | |
| 2026-10-04 08:00 | alive | 1.4 s | 4 | 535 | |
| 2026-10-03 20:39 | alive | 1.5 s | 4 | 535 | |
| 2026-10-03 17:55 | alive | 1.2 s | 4 | 535 |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.sattyamjjain/whycant)
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.