About LLM Usage
LLM Usage is an MCP server in the Commerce category: local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP.
Install
uvx llm-usage-mcppip install llm-usage-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
compare_providersGiven a hypothetical workload (tokens in / out), rank every priced model by cost.
Parameters not published.
get_pricingInspect the vendored pricing snapshot.
Parameters not published.
list_providersList providers + their models + OpenAI-compatibility flag.
Parameters not published.
query_spendTotals + per-group rollups over a time window (group by provider / model / project / tag / day).
Parameters not published.
recommend_providerPick the cheapest priced model that fits a stated budget.
Parameters not published.
record_usageManual write path — log a call when the capture proxy isn't in the picture.
Parameters not published.
usage_summaryHeadline summary for `today` / `week` / `month` / `year` — totals, top-N providers + models, largest call.
Parameters not published.
Ask AI
Ask AI about LLM Usage
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.