llmkit-mcp-server
@f3d1/llmkit-mcp-server
Claude Code, Cline, Cursor 및 Claude Desktop을 위한 AI 비용 추적 도구입니다. 지출 조회, 예산, 로컬 세션 비용 및 11개 LLM 제공업체 전반의 에이전트 기여도 분석을 위한 11가지 도구를 제공합니다.
비용 추적 및 예산 집행 기능을 갖춘 오픈 소스 API 게이트웨이인 LLMKit의 일부입니다.
빠른 시작
.mcp.json(Claude Code) 또는 .cursor/mcp.json(Cursor)에 추가하세요:
{
"mcpServers": {
"llmkit": {
"command": "npx",
"args": ["@f3d1/llmkit-mcp-server"],
"env": {
"LLMKIT_API_KEY": "llmk_your_key_here"
}
}
}
}로컬 도구(llmkit_local_*)는 API 키 없이 즉시 작동합니다. 이 도구들은 사용자의 컴퓨터에서 Claude Code, Cline 및 Cursor 데이터를 자동으로 감지합니다. 프록시 도구를 사용하려면 대시보드에서 무료 키를 생성하세요.
Related MCP server: Langfuse MCP Server
도구
프록시 도구 (API 키 필요)
도구 | 기능 |
| 특정 기간의 지출, 요청 수, 상위 모델 |
| 제공업체, 모델, 세션 또는 일별로 그룹화된 비용 |
| 예산 한도 및 잔액 |
| 비용, 기간, 모델을 포함한 최근 세션 |
| 상태 및 생성 날짜를 포함한 모든 키 |
| 응답 시간을 포함한 프록시 핑 |
로컬 도구 (키 불필요)
설치된 AI 코딩 도구를 자동으로 감지하고 모든 데이터를 집계합니다.
도구 | 기능 |
| 감지된 모든 도구의 현재 세션 비용 |
| 모든 프로젝트 및 세션의 누적 비용 |
| 프롬프트 캐싱 절감액 분석 |
| 월간 예상 비용 vs 최대 구독료 |
| 서브 에이전트 비용 기여도 (Claude Code) |
SessionEnd 훅
Claude Code 종료 시 세션 비용을 자동으로 기록합니다:
{
"hooks": {
"SessionEnd": [
{
"type": "command",
"command": "npx @f3d1/llmkit-mcp-server --hook"
}
]
}
}환경 변수
변수 | 필수 여부 | 설명 |
| 아니요 | 프록시 도구용 API 키. 로컬 도구는 키 없이 작동합니다. |
| 아니요 | 프록시 URL (기본값은 호스팅 서비스) |
| 아니요 | Cline 데이터 디렉토리 경로 재정의 |
지원되는 도구
로컬 도구는 다음 데이터 소스를 감지합니다:
Claude Code (
~/.claude/projects/)Cline (VS Code, Insiders, VSCodium, Cursor, Windsurf globalStorage)
WSL 설치 (Windows의 UNC 경로를 통해 모든 배포판 스캔)
VS Code Server / Cursor Server (원격 SSH/WSL 확장)
라이선스
MIT
Available Tools
11 toolsllmkit_budget_statusARead-onlyIdempotent
Check budget limits and remaining balance
Inputs: budgetId. Returns: budgets
llmkit_cost_queryBRead-onlyIdempotent
Query cost breakdown grouped by provider, model, session, or day
Inputs: groupBy (required), days, provider, model. Returns: groupBy, days, breakdown
llmkit_healthARead-onlyIdempotent
Check proxy health and response time
Inputs: no named parameters. Returns: status, responseTimeMs
llmkit_list_keysARead-onlyIdempotent
List all API keys with status and creation date
Inputs: no named parameters. Returns: keys
llmkit_local_agentsARead-onlyIdempotent
Subagent cost attribution for the current Claude Code session. Shows which agents cost the most.
Inputs: no named parameters. Returns: sessionId, totalCostUsd, mainConversationCostUsd, subagentsTotalCostUsd, +2 more
llmkit_local_cacheARead-onlyIdempotent
Cache savings analysis across all detected AI coding tools. Shows how much prompt caching saved.
Inputs: no named parameters. Returns: savings, totalSavedUsd
llmkit_local_forecastARead-onlyIdempotent
Monthly cost projection based on local AI tool usage. Compares to Max subscription.
Inputs: no named parameters. Returns: projectedMonthlyUsd, dailyAverageUsd, totalTrackedUsd, totalSessions, +1 more
llmkit_local_projectsARead-onlyIdempotent
Cumulative cost across all projects and sessions from all detected AI coding tools, ranked by spend.
Inputs: no named parameters. Returns: projects, totalCostUsd
llmkit_local_sessionARead-onlyIdempotent
Current session cost across all detected AI coding tools (Claude Code, Cline). No API key needed.
Inputs: no named parameters. Returns: sessions, totalCostUsd, sourceCount
llmkit_session_summaryARead-onlyIdempotent
Get recent proxy sessions with cost, duration, and models used
Inputs: sessionId, limit. Returns: sessions
llmkit_usage_statsCRead-onlyIdempotent
Get usage statistics (spend, requests, top models) for a time period
Inputs: period. Returns: period, requests, totalSpendUsd, inputTokens, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Tools are mostly distinct, targeting different aspects like budget, cost breakdown, health, keys, local session, etc. However, llmkit_cost_query, llmkit_usage_stats, and llmkit_session_summary have overlapping purposes (cost/spend/usage data) which could cause some confusion.
All tools follow a consistent pattern with the 'llmkit_' prefix and descriptive noun phrases separated by underscores, e.g., llmkit_budget_status, llmkit_cost_query. No mixing of conventions.
With 11 tools, the count is well within the recommended 3-15 range. Each tool covers a distinct aspect of proxy cost monitoring and management, justifying its inclusion.
The tool surface covers major monitoring needs: health, budget, cost, keys, sessions, and local attribution. However, it lacks management capabilities (e.g., create/update keys or budgets) and could include actions like setting usage limits, which are minor gaps for a read-only analytics server.
Maintenance
Related MCP Connectors
Query cloud, AI and SaaS spend across 25+ providers: costs, budgets, anomalies, unit economics.
AI spend by team, developer and API key for Claude, OpenAI, Gemini and coding agents.
Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more.
FinOps assistant: query AWS, GCP and Azure cost, commitments, budgets and reports.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables interaction with Google Cloud services including billing cost analysis, log querying, and metrics monitoring through natural language commands. Provides comprehensive tools for managing GCP resources, analyzing costs, detecting anomalies, and retrieving operational insights.401Apache 2.0
- AlicenseBqualityDmaintenanceEnables querying Langfuse analytics, cost metrics, and usage data across multiple projects. Provides tools for trace analysis, model/service cost breakdowns, and daily usage trends through natural language queries.2473 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables querying and analyzing AWS cost and usage data through the AWS Cost Explorer API. Supports cost comparisons, forecasting, dimension filtering, and cost change driver analysis with streamable HTTP deployment to Amazon Bedrock Agentcore Runtime.-
- AlicenseBqualityCmaintenanceAn MCP server for unified cost tracking and analysis across AWS, OpenAI, and Anthropic. It enables users to query expenditures, compare costs across providers, and analyze usage trends through natural language.10MIT