CostForge - Autonomous LLM Token, Model Routing & Cloud FinOps MCP
Universal LLM token optimization, prompt caching & cloud FinOps engine for Cursor, Claude Code & Windsurf. Reduces AI t…
Live
Open / InstallLast updated October 8, 2026
Description
Universal LLM token optimization, prompt caching & cloud FinOps engine for Cursor, Claude Code & Windsurf. Reduces AI token bills by 50-80% through semantic prompt compression, automated model cascade routers (Claude 3.5 / Haiku / DeepSeek), Anthropic ephemeral cache breakpoints, and serverless compute audits.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
tofan96you
Platform
mcp
Pricing model
free
Categories
- mcp
Tags
- mcp
- smithery
Capabilities
- Remote MCP server
Information
TypeMCP Server
SourceSmithery
AddedOctober 8, 2026