LLM Cost Estimator runs on your own machine — the client starts it, so there is no endpoint to ping. 29 installs a week from npm. Last commit 21 Jun 2026.
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
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 llm-cost-estimator -- npx -y llm-cost-estimator-mcp
{
"mcpServers": {
"llm-cost-estimator": {
"args": [
"-y",
"llm-cost-estimator-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.llm-cost-estimator]
command = "npx"
args = ["-y", "llm-cost-estimator-mcp"]
{
"mcpServers": {
"llm-cost-estimator": {
"args": [
"-y",
"llm-cost-estimator-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"llm-cost-estimator": {
"args": [
"-y",
"llm-cost-estimator-mcp"
],
"command": "npx"
}
}
}
Answers built from our own checks of this server.