Skip to main content
Glama
llmkit-mcp-server

llmkit-mcp-server

by smigolsmigol

@f3d1/llmkit-mcp-server

针对 Claude Code、Cline、Cursor 和 Claude Desktop 的 AI 成本跟踪工具。提供 11 种工具,用于跨 11 家 LLM 提供商进行支出查询、预算管理、本地会话成本统计和代理归因分析。

这是 LLMKit 的一部分,LLMKit 是一个具有成本跟踪和预算执行功能的开源 API 网关。

快速开始

添加到你的 .mcp.json (Claude Code) 或 .cursor/mcp.json (Cursor) 中:

{
  "mcpServers": {
    "llmkit": {
      "command": "npx",
      "args": ["@f3d1/llmkit-mcp-server"],
      "env": {
        "LLMKIT_API_KEY": "llmk_your_key_here"
      }
    }
  }
}

本地工具 (llmkit_local_*) 无需 API 密钥即可立即使用。它们会自动检测你机器上的 Claude Code、Cline 和 Cursor 数据。对于代理工具,请在 仪表板 创建一个免费密钥。

Related MCP server: Langfuse MCP Server

工具

代理工具(需要 API 密钥)

工具

功能

llmkit_usage_stats

指定时间段内的支出、请求数和热门模型

llmkit_cost_query

按提供商、模型、会话或日期分组的成本查询

llmkit_budget_status

预算限额和剩余余额

llmkit_session_summary

包含成本、持续时间和模型的近期会话摘要

llmkit_list_keys

所有密钥的状态和创建日期

llmkit_health

带有响应时间的代理 ping 测试

本地工具(无需密钥)

自动检测已安装的 AI 编码工具并汇总所有数据。

工具

功能

llmkit_local_session

所有已检测工具的当前会话成本

llmkit_local_projects

所有项目和会话的累计成本

llmkit_local_cache

提示词缓存节省分析

llmkit_local_forecast

月度预测与最大订阅额度对比

llmkit_local_agents

子代理成本归因 (Claude Code)

SessionEnd 钩子

在 Claude Code 退出时自动记录会话成本:

{
  "hooks": {
    "SessionEnd": [
      {
        "type": "command",
        "command": "npx @f3d1/llmkit-mcp-server --hook"
      }
    ]
  }
}

环境变量

变量

必需

描述

LLMKIT_API_KEY

否

代理工具的 API 密钥。本地工具无需此项即可工作。

LLMKIT_PROXY_URL

否

代理 URL(默认为托管服务)

LLMKIT_CLINE_DIR

否

覆盖 Cline 数据目录路径

支持的工具

本地工具可检测以下数据:

  • Claude Code (~/.claude/projects/)

  • Cline (VS Code, Insiders, VSCodium, Cursor, Windsurf globalStorage)

  • WSL 安装(通过 Windows 上的 UNC 路径扫描所有发行版)

  • VS Code Server / Cursor Server (远程 SSH/WSL 扩展)

许可证

MIT

Available Tools

11 tools
llmkit_budget_statusA
Read-onlyIdempotent

Check budget limits and remaining balance

Inputs: budgetId. Returns: budgets

llmkit_cost_queryB
Read-onlyIdempotent

Query cost breakdown grouped by provider, model, session, or day

Inputs: groupBy (required), days, provider, model. Returns: groupBy, days, breakdown

llmkit_healthA
Read-onlyIdempotent

Check proxy health and response time

Inputs: no named parameters. Returns: status, responseTimeMs

llmkit_list_keysA
Read-onlyIdempotent

List all API keys with status and creation date

Inputs: no named parameters. Returns: keys

llmkit_local_agentsA
Read-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_cacheA
Read-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_forecastA
Read-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_projectsA
Read-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_sessionA
Read-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_summaryA
Read-onlyIdempotent

Get recent proxy sessions with cost, duration, and models used

Inputs: sessionId, limit. Returns: sessions

llmkit_usage_statsC
Read-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

    A3.7/5.0

    Scored across 11 tools

    Disambiguation4/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      D
      maintenance
      Enables 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.
      40
      1
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      Enables 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.
      24
      73 npm
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables 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.
      -
    • A
      license
      B
      quality
      C
      maintenance
      An 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.
      10
      MIT