MCP Server

The Revenium MCP Server is the fastest way to connect AI agents — like Claude — directly to your Revenium account

The Revenium MCP Server is the fastest way to connect AI agents — like Claude — directly to your Revenium account. Instead of building dashboards and running manual queries, you ask your AI assistant in plain English: "What's driving my AI cost spike this week?" or "Set up an alert if any single transaction exceeds $5." The MCP server handles the rest.

This is MCP-first integration: Revenium's capabilities surface as native tools inside your AI assistant's context, so cost intelligence and governance become part of every conversation

What You Can Do With the MCP Server

Once connected, your AI agent can:

• Investigate cost spikes — ask "Why did my costs spike yesterday?" and get a breakdown by provider, model, customer, agent, or API key

• Detect anomalies — find abnormal spend patterns across all dimensions, with configurable sensitivity and dollar thresholds

• Set budget alerts — trigger Slack or email notifications when monthly, daily, or per-transaction spend exceeds a threshold

• Monitor trends — get cost summaries for any time window (last hour, day, week, or month) broken down any way you need

• Catch cost increases early — set relative-change alerts that fire when spend rises or falls by a percentage week-over-week or month-over-month

• Surface AI-driven cost recommendations — run and review Revenium's AI Insights recommendation engine to flag waste, concentration risk, reliability issues, and efficiency opportunities across your usage

• Meter its own usage — track the agent's own API calls back to your Revenium account for full operational transparency

• Integrate metering into your app — get working code examples and implementation guidance for Python and JavaScript without leaving your IDE

• Track agent job ROI — measure the business outcomes and return on investment of individual AI agent jobs

Getting Started

Install uv (pip install uv) and add this to your MCP client config:

{
  "mcpServers": {
    "revenium": {
      "command": "uvx",
      "args": ["revenium-mcp"],
      "env": {
        "REVENIUM_API_KEY": "rev_sk_your_api_key_here"
      }
    }
  }
}

The MCP server needs a write-scope key (rev_sk_*) because it both reads Revenium data and can create alerts and modify resources — a metering-only key (rev_mk_*) will be rejected. See API Key Permissions for the full key tier reference.

The MCP server is open source. The uvx install above runs it locally per developer, or your team can deploy a shared instance using the Dockerfile and docker-compose templates in the Revenium MCP server repository. The same repository covers Claude Code shortcuts, IDE-specific install variants, troubleshooting, and the full configuration reference.

Related

• Rancher Prime Integration — Kubernetes in-cluster deployment

• Context7 and AI Docs Access — AI-readable docs access without running an MCP server