LLM Cost
Verified IntegrationClient Configuration
— Connect LLM Cost to Claude Desktop or Cursor in seconds{
"mcpServers": {
"llm-cost": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-llm-cost"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Calculates real-time token costs and estimates spending for large language model API calls across a wide range of providers.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for LLM Cost
No, LLM Cost operates entirely via local computation using a public price feed. This means no API keys are needed, there are no rate limits, and it offers resilience against network issues by serving the last good copy of prices.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.