Passive Cost Memory for Agent Development
@RaleighSF
Passive Cost Memory for Agent Development について
Burnwatch detects every paid service in your project, tracks spend across 14 AI-native tools (Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, and more), and exposes real-time cost data via MCP tools — so any LLM can factor budget into its recommendations. Four
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"burnwatch": {
"command": "node",
"args": [
"node_modules/burnwatch/dist/mcp-server.js"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Passive Cost Memory for Agent Development?
Passive Cost Memory for Agent Development (burnwatch) is a cost monitoring tool for agent projects that provides spend overviews, service deep dives, and paid-service scans across 14 supported services like Anthropic, OpenAI, and AWS.
How to use Passive Cost Memory for Agent Development?
Install via npm install burnwatch, then add a configuration entry to your MCP client with the command node and args ["node_modules/burnwatch/dist/mcp-server.js"].
Key features of Passive Cost Memory for Agent Development
- Full project spend overview with budget alerts
- Deep dive on any service with gotchas and alternatives
- Scan a project for all paid services
- Browse a registry of 14 supported services
- Confidence badges (LIVE, CALC, EST, BLIND) indicate data quality
Use cases of Passive Cost Memory for Agent Development
- Monitor total project spending and catch budget overruns early
- Analyze cost breakdown for individual services to optimize spending
- Discover all paid services used across a project
- Get alternatives and gotchas for each supported service
FAQ from Passive Cost Memory for Agent Development
What services does it support?
Anthropic, OpenAI, Vercel, Supabase, Stripe, Scrapfly, Browserbase, Upstash, Resend, Inngest, PostHog, Google Gemini, Voyage AI, and AWS, with more coming.
How are spend figures categorized?
Each spend figure has a confidence badge: LIVE (real billing API data), CALC (fixed monthly cost, projected), EST (estimated from usage patterns), or BLIND (detected but not yet tracked).
How do I install it?
Run npm install burnwatch and add the MCP server configuration to your client as shown in the README.
What tools does it provide?
Four tools: get_spend_brief, get_service_spend, detect_paid_services, and list_registry_services.
How do I scan a project for paid services?
Use the detect_paid_services tool to scan a project and identify all paid services it uses.
「AI とエージェント」の他のコンテンツ
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
🛡️ A.I.G（AI-Infra-Guard）
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
コメント