Qwen3_8_27B_reference_step – 1 MCP server offers this tool
What it usually takes
generated– in 1 of 1gpu_seconds– in 1 of 1history– in 1 of 1max_new_tokens– in 1 of 1message– in 1 of 1reasoning_effort– in 1 of 1temperature– in 1 of 1top_k– in 1 of 1top_p– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Qwen3.8 27B reference co.huggingface.bottlecapai/qwen3.8-27b-reference Advance one reply by a single ZeroGPU reservation. Call repeatedly to finish it. Returns: Streams {"ids", "seconds", "think_seconds"} for this call so far: the new token ids,, the decode time since this call's first new token, and when (on that clock), `</think>` (id 248069, which separates reasoning from the answer) was generated,, or null. Append the last "ids" to, `generated` and call again until the reply ends with an EOS id (248046 or 248044), or reaches max_new_tokens. | generated,gpu_seconds,history,max_new_tokens,message,reasoning_effort,temperature,top_k,top_p | Not stated |