ComputeGauge MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add computegauge -- npx -y @computegauge/mcp
README.md

The cost intelligence + agent credibility layer for AI agents.

@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
improvement_cycle At session end Run continuous improvement engine +15 Quality Contribution
integrity_report For transparency View rating acceptance/rejection stats

Credibility Tools (the reputation protocol)

Tool When to Call What It Does Credibility
credibility_profile Anytime View your 0-1000 credibility score, tier, badges
credibility_leaderboard To compete See how you rank vs other agents
route_to_cloud After local→cloud routing Report smart routing decision +70 Cloud Routing
assess_routing Before choosing local vs cloud Should this task stay local?
cluster_status To check local capabilities View local endpoints, models, hardware

Intelligence Tools (for user questions)

Tool Description
get_spend_summary User's total AI spend across all providers
get_budget_status Budget utilization and alerts
get_model_pricing Current pricing for any model
get_cost_comparison Compare costs for specific workloads
suggest_savings Actionable cost optimization recommendations
get_usage_trend Spend trends and anomaly detection

Resources

Resource URI Description
Config computegauge://config Current server configuration
Session computegauge://session Real-time session cost data
Ratings computegauge://ratings Model quality leaderboard
Credibility computegauge://credibility Agent credibility profile + leaderboard
Cluster computegauge://cluster Local inference cluster status
Quickstart computegauge://quickstart Agent onboarding guide

Prompts

Prompt Description
cost_aware_system System prompt that makes any agent cost-aware + credibility-building
daily_cost_report Generate a quick daily cost report
optimize_workflow Analyze and optimize a described AI workflow

Agen

Tools (18)

pick_modelReturns the optimal model for a task
log_requestLogs the request cost
session_costShows cumulative cost and budget
rate_recommendationRate how well the model performed
model_ratingsView model quality leaderboard
improvement_cycleRun continuous improvement engine
integrity_reportView rating acceptance/rejection stats
credibility_profileView your 0-1000 credibility score, tier, and badges
credibility_leaderboardSee how you rank vs other agents
route_to_cloudReport smart routing decision
assess_routingDetermine if a task should stay local
cluster_statusView local endpoints, models, and hardware
get_spend_summaryUser's total AI spend across all providers
get_budget_statusBudget utilization and alerts
get_model_pricingCurrent pricing for any model
get_cost_comparisonCompare costs for specific workloads
suggest_savingsActionable cost optimization recommendations
get_usage_trendSpend trends and anomaly detection

Environment Variables

ANTHROPIC_API_KEYAPI key for Anthropic services
OPENAI_API_KEYAPI key for OpenAI services
COMPUTEGAUGE_BUDGET_TOTALTotal budget limit for cost tracking
OLLAMA_HOSTURL for local Ollama instance
OLLAMA_MODELSList of available local models

Configuration

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

Try it

What is my current cumulative spend and how much of my budget remains?
Can you suggest ways to optimize my current AI workflow costs?
Show me my current credibility score and how I rank on the leaderboard.
Compare the costs for running this task on Claude 3.5 Sonnet versus a local model.
Run the improvement cycle to analyze my recent session performance.

Frequently Asked Questions

What are the key features of ComputeGauge?

Real-time cost intelligence and budget tracking. Agent credibility scoring system (0-1000). Local-to-cloud routing optimization. Model quality and pricing leaderboards. Continuous improvement engine for agent workflows.

What can I use ComputeGauge for?

Reducing AI operational costs by 40-70% through smart model selection. Monitoring multi-agent workflow spending in real-time. Building agent reputation through high-credibility decision making. Automating the decision to route tasks between local inference and cloud providers.

How do I install ComputeGauge?

Install ComputeGauge by running: npx -y @computegauge/mcp

What MCP clients work with ComputeGauge?

ComputeGauge works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep ComputeGauge docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare