dev.promplate/hmr
hmr-docs
Docs for hot-module-reload and reactive programming for Python (`hmr` on PyPI)
alive probed 2026-10-05 · HTTP 200
3tools
607tokens in Claude Opus 5.5
631tokens in Claude Code
0.3 %of a 200k context window
396o200k_base estimate
610 msto initialize
156 msto list tools
- Endpoint
- https://pyth-on-line.promplate.dev/hmr/mcp (streamable-http)
- Host
- pyth-on-line.promplate.dev
- Protocol
- 2025-06-18
- Reports itself as
- hmr-docs 1.0.0
- Capabilities
- prompts, resources, 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/promplate/hmr
- Registry
- active, updated 2025-09-17 · registry entry
- Reachable
- 6 of the last 6 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| view-hmr-core-sources | 163 | 41 % |
| view-hmr-unit-tests | 146 | 37 % |
| learn-hmr-basics | 87 | 22 % |
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 13:59 | alive | 610 ms | 3 | 607 | 396 |
| 2026-10-05 00:24 | alive | 402 ms | 3 | 396 | |
| 2026-10-04 10:00 | alive | 1.0 s | 3 | 396 | |
| 2026-10-04 07:53 | alive | 1.3 s | 3 | 396 | |
| 2026-10-03 20:33 | alive | 941 ms | 3 | 396 | |
| 2026-10-03 17:50 | alive | 290 ms | 3 | 396 |
Badge and feed
[](https://mcpcost.ulehla.dev/s/dev.promplate/hmr)
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.