AI Cost Analyzer runs on your own machine — the client starts it, so there is no endpoint to ping. 8 installs a week from npm.
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ai-cost-analyzer -- npx -y ai-cost-analyzer
{
"mcpServers": {
"ai-cost-analyzer": {
"args": [
"-y",
"ai-cost-analyzer"
],
"command": "npx"
}
}
}
[mcp_servers.ai-cost-analyzer]
command = "npx"
args = ["-y", "ai-cost-analyzer"]
{
"mcpServers": {
"ai-cost-analyzer": {
"args": [
"-y",
"ai-cost-analyzer"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ai-cost-analyzer": {
"args": [
"-y",
"ai-cost-analyzer"
],
"command": "npx"
}
}
}
LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
Password strength scoring with entropy, crack time estimation, common password detection. x402.
Automated time series forecasting with model search, anomaly detection, and event risk analysis
Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
Analyze your MCP setup: token costs, grades, duplicates, and optimization tips
Answers built from our own checks of this server.