llmkit_budget_status
Check budget limits and remaining balance
LABSCO SUMMARY
Cost attribution for coding agents that works before you sign up for anything.
The local tools are the immediate payoff: they read what Claude Code and Cline already record and answer what this session cost, which project has consumed the most, how much caching saved, and — less commonly available — which subagent inside the current session is doing the spending. The gateway half adds shared budgets with admission control, where estimated spend is reserved before the request leaves and an over-budget request is rejected rather than discovered later; that half needs a key the project says it cannot currently issue.
What it is
A cost server with two halves. The local half reads the session data Claude Code and Cline already write on your machine and needs no account. The gateway half queries an LLMKit proxy, which reserves estimated spend before dispatching a request and refuses one that will not fit the budget.
What you get
- llmkit_local_session totals the current session's cost across every AI coding tool it detects, with no API key involved
- llmkit_local_projects ranks cumulative cost across all projects and sessions by spend
- llmkit_local_agents attributes cost to individual subagents inside the current Claude Code session, so an expensive one is identifiable rather than merely suspected
- llmkit_local_cache reports how much prompt caching actually saved across the detected tools
- llmkit_local_forecast projects a monthly cost from local usage and compares it against a Max subscription
- llmkit_usage_stats returns spend, request count and top models for a period, and llmkit_cost_query breaks the same spend down by provider, model, session or day
- llmkit_budget_status reports budget limits and remaining balance, and llmkit_session_summary lists recent proxy sessions with cost, duration and models used
- llmkit_list_keys shows API keys with status and creation date, and llmkit_health checks proxy reachability and response time
Requirements
Published as @f3d1/llmkit-mcp-server and launched over stdio with npx. The local tools require nothing at all — they read session files the coding tools already produce. The gateway tools need an existing LLMKit API key, and the repository states that account creation and key management are temporarily unavailable while the authenticated service is restored, so without a key already in hand the local half is what works.
Setup effort
One command — npx -y @f3d1/llmkit-mcp-server
USE CASES
01
Knowing what this session has cost so far
One call totals the current session across every detected coding tool, with nothing to configure first.
02
Finding where the money actually goes
Projects ranked by cumulative spend, and inside the current session, the subagents that account for it.
03
Checking whether prompt caching is earning its keep
llmkit_local_cache puts a figure on what caching saved rather than leaving it as an assumption.
04
Deciding between metered billing and a subscription
The forecast projects the month from your real local usage and sets it against a Max subscription.
05
Reporting on gateway spend
Totals and top models for a period, then the same spend grouped by provider, model, session or day.
06
Checking there is budget before a long run
Budget limits and remaining balance, plus a proxy health check so a failure later is not a surprise.
11 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
llmkit_cost_query
Query cost breakdown grouped by provider, model, session, or day
llmkit_health
Check proxy health and response time
llmkit_list_keys
List all API keys with status and creation date
llmkit_local_agents
Subagent cost attribution for the current Claude Code session. Shows which agents cost the most.
llmkit_local_cache
Cache savings analysis across all detected AI coding tools. Shows how much prompt caching saved.
llmkit_local_forecast
Monthly cost projection based on local AI tool usage. Compares to Max subscription.
llmkit_local_projects
Cumulative cost across all projects and sessions from all detected AI coding tools, ranked by spend.
llmkit_local_session
Current session cost across all detected AI coding tools (Claude Code, Cline). No API key needed.
llmkit_session_summary
Get recent proxy sessions with cost, duration, and models used
llmkit_usage_stats
Get usage statistics (spend, requests, top models) for a time period
BEFORE YOU INSTALL
What to know first
Tools you get
11 tools when we connected.
Requires
npx on PATH
Optional
LLMKIT_API_KEY in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 11 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"llmkit-mcp-server": {
"command": "npx",
"args": [
"-y",
"@f3d1/llmkit-mcp-server"
]
}
}
}LLMKIT_API_KEY is optional and only for the six gateway tools; the five local tools need no key. If you have one, set LLMKIT_API_KEY in the server's environment: in a config file, add an "env" entry with it next to "args"; on the command line, export it before running npx.
npx
TERMINAL
npx -y @f3d1/llmkit-mcp-server
