What's new in v1.1.0
Packaging
- Renamed the Python package
server/→quelllm_mcp/with a propermain()console entry point. The old top-levelserverpackage name risked import collisions on user machines. Config and install are unchanged (command: "quelllm-mcp").
Bug fixes
compare(): removed thetokSecfield (it never existed in the quelllm.fr API, so it was alwaysnull) and exposed the realctx(context window) instead. Replaced the bogusmore_recentplaceholder — which actually compared parameter counts — with honestmore_paramsandlarger_contextsignals._fetch_json: now serves a stale cache entry when quelllm.fr is unreachable, instead of crashing the tool call with a raw stack trace.
Cost estimator
estimate_costgained prompt-caching, batch mode, DeepSeek off-peak discounts, a token-capacity check for self-hosted hardware, recoverable-VAT andpc_always_ontoggles — matching the web calculator at https://quelllm.fr/calculateur-cout-llm.
Docs / metadata
- Removed the phantom PyPI package declaration from
server.json(the package is not published on PyPI). Documented install viapip install git+…anduvx. - Corrected the catalog size claim from "250+" to "190+" across README,
pyproject.tomlandserver.json.
Install
pip install git+https://github.com/MGM-FALCON/quelllm-mcp.git