io.github.sachinuppal/modelcostsaver MCP Server

io.github.sachinuppal/modelcostsaver

Repository Registry

What is the io.github.sachinuppal/modelcostsaver MCP server?

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

How to install io.github.sachinuppal/modelcostsaver

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "modelcostsaver": {
      "command": "npx",
      "args": [
        "-y",
        "@workswarm/modelcostsaver"
      ]
    }
  }
}

Related MCP servers

io.github.sachitrafa/cognitive-ai-memory

Active

Ebbinghaus-based persistent memory for Claude—memories decay with time, strengthen on recall.

263

Python

View repository →

YourMemory

Active

Persistent, self-improving memory for AI agents with biological decay and consolidation—your AI remembers across sessions.

263

Python

View repository →

io.github.sacravenger/nanmesh-mcp

Active

12 tools that let AI agents check trust scores and reviews before recommending any software tool.

JavaScript

View repository →

Redra

Active

Search current class-action settlements and identify possible matches using structured filters.

Python

MIT

View repository →

ABA routing 9-digit shape, value discarded

Active

ABA routing 9-digit shape, value discarded

View repository →

ABNF rule count, body discarded

Active

ABNF rule count, body discarded

View repository →