io.github.stevecrates489-commits/tokcalc
tokcalc MCP Server
LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.
error probed 2026-10-05 · HTTP 400
Streamable HTTP error: Error POSTing to endpoint: {"jsonrpc":"2.0","error":{"code":-32600,"message":"Missing MCP-Protocol-Version header","data":{"detail":"Stre- Endpoint
- https://tokcalc.vercel.app/api/mcp (streamable-http)
- Host
- tokcalc.vercel.app
- Repository
- https://github.com/stevecrates489-commits/tokcalc
- Registry
- active, updated 2026-10-03 · registry entry
- Reachable
- 0 of the last 5 probes
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 00:56 | error | ||||
| 2026-10-04 10:07 | error | ||||
| 2026-10-04 08:00 | error | ||||
| 2026-10-03 20:40 | error | ||||
| 2026-10-03 17:55 | error |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.stevecrates489-commits/tokcalc)
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.