CM

computegauge/mcp

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

0 stars 2 forks Качество 71 Тренд 0Apache-2.0

The cost intelligence layer for AI agents. Model selection, spend tracking, credibility scoring, and local-to-cloud routing via MCP.

Обзор

Install once, every session is cost-aware and credibility-building. AI agents are powerful but expensive. A single Claude Code session can cost $5-50+. A multi-agent workflow can burn through $100 in minutes. And nobody tells the agent — or the human — until the bill arrives. Any MCP-compatible agent (Claude, Cursor, Windsurf, custom agents) gets: 1. — Know which model is optimal for every task, track spend in real-time 2. — Build a reputation score (0-1000) by making smart decisions. Compete on a leaderboard. 3. — Detect when local inference isn't good enough, route to cloud, earn credibility for smart routing The result: agents that spend 40-70% less, build visible credibility, and know when to route to cloud. Add to ~/.config/claude/claude_desktop_config.json: That's it. Restart Claude. Every conversation now has cost intelligence + credibility tracking. Every smart decision earns credibility points on a 0-1000 scale:

README

Показан фрагмент оригинального README. Открыть оригинал.

@computegauge/mcp

The cost intelligence + agent credibility layer for AI agents. Install once, every session is cost-aware and credibility-building.

npm install -g @computegauge/mcp

Why This Exists

AI agents are powerful but expensive. A single Claude Code session can cost $5-50+. A multi-agent workflow can burn through $100 in minutes. And nobody tells the agent — or the human — until the bill arrives.

ComputeGauge MCP makes agents cost-aware AND gives them a credibility score. Any MCP-compatible agent (Claude, Cursor, Windsurf, custom agents) gets:

  1. Cost Intelligence — Know which model is optimal for every task, track spend in real-time
  2. Agent Credibility — Build a reputation score (0-1000) by making smart decisions. Compete on a leaderboard.
  3. Local→Cloud Routing — Detect when local inference isn’t good enough, route to cloud, earn credibility for smart routing

The result: agents that spend 40-70% less, build visible credibility, and know when to route to cloud.


Setup — 30 Seconds

Claude Desktop / Claude Code

Add to ~/.config/claude/claude_desktop_config.json:

{
  "mcpServers": {
    "computegauge": {
      "command": "npx",
      "args": ["-y", "@computegauge/mcp"]
    }
  }
}

That’s it. Restart Claude. Every conversation now has cost intelligence + credibility tracking.

With Provider API Keys (Enhanced)

{
  "mcpServers": {
    "computegauge": {
      "command": "npx",
      "args": ["-y", "@computegauge/mcp"],
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-...",
        "OPENAI_API_KEY": "sk-...",
        "COMPUTEGAUGE_BUDGET_TOTAL": "50"
      }
    }
  }
}

With Local Inference (Ollama, vLLM, etc.)

{
  "mcpServers": {
    "computegauge": {
      "command": "npx",
      "args": ["-y", "@computegauge/mcp"],
      "env": {
        "OLLAMA_HOST": "http://localhost:11434",
        "OLLAMA_MODELS": "llama3.3:70b,qwen2.5:7b,deepseek-r1:14b",
        "ANTHROPIC_API_KEY": "sk-ant-...",
        "COMPUTEGAUGE_BUDGET_TOTAL": "50"
      }
    }
  }
}

Cursor

Add to Cursor MCP settings:

{
  "computegauge": {
    "command": "npx",
    "args": ["-y", "@computegauge/mcp"]
  }
}

Tools Reference

Agent-Native Tools (use automatically every session)

Tool When to Call What It Does Credibility
pick_model Before any API request Returns the optimal model for a task +8 Routing Intelligence
log_request After any API request Logs the request cost +3 Honest Reporting
session_cost Every 5-10 requests Shows cumulative cost and budget —
rate_recommendation After completing a task Rate how well the model performed +5 Quality Contribution
model_ratings When curious about quality View model quality leaderboard —
Открыть полный README на GitHub

Установка

npx -y @computegauge/mcp
Новичок в MCP? Начните с руководства на mcpskill.org →

Конфигурация

{ "mcpServers": { "computegauge": { "command": "npx", "args": ["-y", "@computegauge/mcp"] } } }