Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
METRX_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"metrxbots": {
"command": "npx",
"args": [
"-y",
"@metrxbot/mcp-server"
],
"env": {
"METRX_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add metrxbots --env METRX_API_KEY=your-value -- npx -y @metrxbot/mcp-server运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"metrxbots": {
"command": "npx",
"args": [
"-y",
"@metrxbot/mcp-server"
],
"env": {
"METRX_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"metrxbots": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@metrxbot/mcp-server"
],
"env": {
"METRX_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 metrxbots 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:METRX_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.2.2)于8个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Foliosio
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read your support inbox, tag conversations and save draft replies from your AI agent. Never sends.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Your AI agents are wasting money. Metrx finds out how much, and fixes it.
The official MCP server for Metrx — the AI Agent Cost Intelligence Platform. Give any MCP-compatible agent (Claude, GPT, Gemini, Cursor, Windsurf) the ability to track its own costs, detect waste, optimize model selection, and prove ROI.
| Problem | What Metrx Does |
|---|---|
| No visibility into agent spend | Real-time cost dashboards per agent, model, and provider |
| Overpaying for LLM calls | Provider arbitrage finds cheaper models for the same task |
| Runaway costs | Budget enforcement with auto-pause when limits are hit |
| Wasted tokens | Cost leak scanner detects retry storms, context bloat, model mismatch |
| Can't prove AI ROI | Revenue attribution links agent actions to business outcomes |
npx @metrxbot/mcp-server --demo
This starts the server with sample data so you can explore all 23 tools instantly.
Option A — Interactive login (recommended):
npx @metrxbot/mcp-server --auth
Opens your browser to get an API key, validates it, and saves it to ~/.metrxrc so you never need to set env vars.
Option B — Environment variable:
METRX_API_KEY=sk_live_your_key_here npx @metrxbot/mcp-server --test
Get your free API key at app.metrxbot.com/sign-up.
If you used --auth, no env block is needed — the key is read from ~/.metrxrc automatically:
{
"mcpServers": { "metrx": { "command": "npx", "args": ["@metrxbot/mcp-server"] } } }
Or pass the key explicitly via environment:
{
"mcpServers": { "metrx": { "command": "npx", "args": ["@metrxbot/mcp-server"], "env": { "METRX_API_KEY": "sk_live_your_key_here" } } } }
For remote agents (no local install needed):
POST https://metrxbot.com/api/mcp
Authorization: Bearer sk_live_your_key_here Content-Type: application/json
npm install @metrxbot/mcp-server
| Tool | Description |
|---|---|
metrx_get_cost_summary | Comprehensive cost summary — total spend, call counts, error rates, and optimization opportunities |
metrx_list_agents | List all agents with status, category, cost metrics, and health indicators |
metrx_get_agent_detail | Detailed agent info including model, framework, cost breakdown, and performance history |
| Tool | Description |
|---|---|
metrx_get_optimization_recommendations | AI-powered cost optimization recommendations per agent or fleet-wide |
metrx_apply_optimization | One-click apply an optimization recommendation to an agent |
metrx_route_model | Model routing recommendation for a specific task based on complexity |
metrx_compare_models | Compare LLM model pricing and capabilities across providers |
| Tool | Description |
|---|---|
metrx_get_budget_status | Current status of all budget configurations with spend vs. limits |
metrx_set_budget | Create or update a budget with hard, soft, or monitor enforcement |
metrx_update_budget_mode | Change enforcement mode of an existing budget or pause/resume it |
| Tool | Description |
|---|---|
metrx_get_alerts | Active alerts and notifications for your agent fleet |
metrx_acknowledge_alert | Mark one or more alerts as read/acknowledged |
metrx_get_failure_predictions | Predictive failure analysis — identify agents likely to fail before it happens |
| Tool | Description |
|---|---|
metrx_create_model_experiment | Start an A/B test comparing two LLM models with traffic splitting |
metrx_get_experiment_results | Statistical significance, cost delta, and recommended action |
metrx_stop_experiment | Stop a running model routing experiment and lock in the winner |
| Tool | Description |
|---|---|
metrx_run_cost_leak_scan | Comprehensive 7-check cost leak audit across your entire agent fleet |
| Tool | Description |
|---|---|
metrx_attribute_task | Link agent actions to business outcomes for ROI tracking |
metrx_get_task_roi | Calculate return on investment for an agent — costs vs. attributed outcomes |
metrx_get_attribution_report | Multi-source attribution report with confidence scores and top contributors |
| Tool | Description |
|---|---|
metrx_configure_alert_threshold | Set cost or operational alert thresholds with email, webhook, or auto-pause |
| Tool | Description |
|---|---|
metrx_generate_roi_audit | Board-ready ROI audit report for your AI agent fleet |
| Tool | Description |
|---|---|
metrx_get_upgrade_justification | ROI report for tier upgrades based on current usage patterns |
Pre-built prompt templates for common workflows:
| Prompt | Description |
|---|---|
analyze-costs | Comprehensive cost overview — spend breakdown, top agents, optimization opportunities |
find-savings | Discover optimization opportunities — model downgrades, caching, routing |
cost-leak-scan | Scan for waste patterns — retry storms, oversized contexts, model mismatch |
User: What was my AI cost this week?
→ metrx_get_cost_summary(period_days=7)
Total Spend: $234.56 | Calls: 2,450 | Error Rate: 0.2% ├── customer-support: $156.23 (1,800 calls) └── code-generator: $78.33 (650 calls)
💡 Switch customer-support from GPT-4 to Claude Sonnet: Save $42/week
User: Am I overpaying for my agents?
→ metrx_compare_models(models=["gpt-4o", "claude-3-5-sonnet", "gemini-1.5-pro"])
Model Comparison (per 1M tokens): ├── gpt-4o: $2.50 in / $10.00 out ├── claude-3-5-sonnet: $3.00 in / $15.00 out └── gemini-1.5-pro: $3.50 in / $10.50 out
User: Test Claude 3.5 Sonnet against my GPT-4 setup
→ metrx_create_model_experiment(agent_id="agent_123", model_a="gpt-4o", model_b="claude-3-5-sonnet-20241022", traffic_split=10)
Experiment started: 90% GPT-4o, 10% Claude 3.5 Sonnet Check back in 14 days for statistical significance.
This repo also includes @metrxbot/cost-leak-detector — a free, offline CLI that scans your LLM API logs for wasted spend. No signup, no cloud, no data leaves your machine.
npx @metrxbot/cost-leak-detector demo
It runs 7 checks (idle agents, premium model overuse, missing caching, high error rates, context overflow, no budgets, arbitrage opportunities) and gives you a scored report in seconds. See the full docs.
The server looks for your API key in this order:
METRX_API_KEY environment variable~/.metrxrc file (created by --auth)Run npx @metrxbot/mcp-server --auth to save your key, or set the env var directly.
| Variable | Required | Description |
|---|---|---|
METRX_API_KEY | Yes* | Your Metrx API key (get one free) |
METRX_API_URL | No | Override API base URL (default: https://metrxbot.com/api/v1) |
*Not required if you've run --auth — the key is read from ~/.metrxrc automatically.
| Flag | Description |
|---|---|
--demo | Start with sample data — no API key or signup needed |
--auth | Interactive login — opens browser, validates key, saves to ~/.metrxrc |
--test | Verify your API key and connection |
60 requests per minute per tool. For higher limits, contact support@metrxbot.com.
git clone https://github.com/metrxbots/mcp-server.git
cd mcp-server npm install npm run typecheck npm test
See CONTRIBUTING.md for guidelines.
The product is Metrx (metrxbot.com). The npm scope is @metrxbot and the Smithery listing is metrxbot/mcp-server. The GitHub organization is metrxbots (with an s) because metrxbot was already taken on GitHub. If you see metrxbot vs metrxbots across platforms, they're the same project — just a GitHub namespace constraint.
MIT — see LICENSE.
Did Metrx work for you? We'd love to hear it — good or bad.
If you installed but hit a snag, tell us what happened — we read every report.