ComparEdge LLM Cost runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 11 Jul 2026.
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
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 comparedge-llm-cost -- npx -y @comparedge/llm-cost-mcp
{
"mcpServers": {
"comparedge-llm-cost": {
"args": [
"-y",
"@comparedge/llm-cost-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.comparedge-llm-cost]
command = "npx"
args = ["-y", "@comparedge/llm-cost-mcp"]
{
"mcpServers": {
"comparedge-llm-cost": {
"args": [
"-y",
"@comparedge/llm-cost-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"comparedge-llm-cost": {
"args": [
"-y",
"@comparedge/llm-cost-mcp"
],
"command": "npx"
}
}
}
Answers built from our own checks of this server.