MCP Cost Optimizer
A local-first MCP server that analyzes LLM usage records to calculate costs and estimate savings from switching models. It helps developers find overspending in AI agent usage, compare model costs, and make data-driven decisions without requiring API keys.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Analyze LLM usage across multiple models
- Compare the cost of different models
- Find overspending in AI agent usage records
- Estimate savings by switching models
Source and maintenance
- Last repository push
- Latest release
- v0.1.2
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
mcp-cost-optimizer 0.1.2
{
"version": "0.1.2",
"transport": "stdio",
"identifier": "mcp-cost-optimizer",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"mcp-cost-optimizer": {
"command": "npx",
"args": [
"-y",
"mcp-cost-optimizer@0.1.2"
]
}
}
}Cline
{
"mcpServers": {
"mcp-cost-optimizer": {
"command": "npx",
"args": [
"-y",
"mcp-cost-optimizer@0.1.2"
]
}
}
}VS Code
{
"servers": {
"mcp-cost-optimizer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-cost-optimizer@0.1.2"
]
}
}
}Claude Desktop
{
"mcpServers": {
"mcp-cost-optimizer": {
"command": "npx",
"args": [
"-y",
"mcp-cost-optimizer@0.1.2"
]
}
}
}Let your agent find its tools
Find servers like MCP Cost Optimizer from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.