forecast_monthly_spendLABSCO SUMMARY
The spike seen before it happens, not explained afterwards.
Reading your own logs, it projects the month with a confidence band and ranks what is actually driving the rate — so the decision to change how you work arrives with days left rather than at the reset.
What it is
A forecaster that reads your local Claude Code logs and projects end-of-month spend from them. Three tools are free and one is paid, and nothing phones home — the logs stay on your machine.
What you get
- Projected end-of-month spend with a low, mid and high confidence band, a rolling average over recent days, and day-of-week seasonality
- The top five subagents, projects or files driving the burn rate, ranked by cost delta per day
- A budget check returning hours until breach, breach risk as a percentage, and a level of clear, warn, urgent or breached
- Model routing, caching and compaction recommendations with the monthly saving projected from your own usage, on the paid tier
Requirements
A recent Python. Not yet on PyPI, so install from source and register mcp-usage-forecaster in your client config. It reads local Claude Code logs, so it runs on the machine you work on. The budget check is capped at three calls a day on the free tier, and the recommendations tool needs MILO_USAGE_FORECASTER_PRO_KEY.
Setup effort
Build from source — git clone https://github.com/miloantaeus/milo-usage-forecaster-mcp.git
USE CASES
01
Finding out whether this month blows the budget
A projected end-of-month figure with a low-to-high band, built from your recent weeks rather than a straight-line guess.
02
Working out what is burning the money
The top five subagents, projects or files by cost per day, which usually names one thing nobody suspected.
03
Knowing when to act
Hours until breach and a breach risk percentage with a level attached, so the alarm arrives before the cap does.
04
Deciding what to change
Routing, caching and compaction recommendations with the projected saving attached, computed from your real usage.
05
Explaining a spike after a heavy week
The rolling average and day-of-week seasonality separate a bad Tuesday from a genuine change in the burn rate.
4 tools
Listed in project docs. Your client may show a different list.
identify_spike_driversbudget_alert_checkoptimize_recommendationsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
mcp-usage-forecaster on PATH
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/miloantaeus/milo-usage-forecaster-mcp.git
cd milo-usage-forecaster-mcp
pip install -e .MCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"milo-usage-forecaster": {
"command": "mcp-usage-forecaster",
"env": {
"MILO_USAGE_FORECASTER_PRO_KEY": ""
}
}
}
}Claude Code — Python
CLAUDE CODE — PYTHON · JSON
{
"mcpServers": {
"milo-usage-forecaster": {
"command": "python",
"args": [
"-m",
"milo_usage_forecaster"
]
}
}
}Other MCP Clients
Cursor, Continue and other MCP-aware tools: add a stdio server whose command is mcp-usage-forecaster, in your client's own MCP config format. The README gives no per-client file for these.
