TokenEyez
See unified AI token usage across Claude, ChatGPT, Gemini, Cursor, and Claude Code to control spend as you scale agent workflows.
Overview
TokenEyez is an MCP server for the Grow phase that tracks AI token usage across Claude, ChatGPT, Gemini, Cursor, and Claude Code.
What is this MCP server?
- TokenEyez MCP (@tokeneyez/mcp) via npx with stdio transport
- Aggregates token tracking across Claude, ChatGPT, Gemini, Cursor, and Claude Code
- Version 0.3.2 in MCP server registry schema
- npm registry package for quick local agent wiring
- Helps solo builders compare burn across multiple AI surfaces
- Server version 0.3.2
- npm package @tokeneyez/mcp
- Transport: stdio
What problem does it solve?
Solo builders split work across many AI apps and lose visibility into total token spend until invoices surprise them.
Who is it for?
Indie developers juggling multiple AI coding and chat products who want MCP-accessible usage tracking without a full FinOps stack.
Skip if: Teams with single-vendor contracts and native billing alerts only, or builders who do not run MCP at all.
What do I get? / Deliverables
After adding TokenEyez via npx, you can query consolidated usage context from your agent and spot heavy tools or sessions earlier.
- Registered TokenEyez MCP server
- Cross-platform token usage views queryable via MCP tools
- Baseline for comparing AI tool burn rates
Recommended MCP Servers
Journey fit
How it compares
Cross-vendor token analytics MCP, not a code indexer or deployment integration.
Common Questions / FAQ
Who is TokenEyez for?
TokenEyez is for solo builders and small teams who use several AI products and want token usage exposed through MCP.
When should I use TokenEyez?
Use it during Grow when you optimize AI spend, compare Cursor versus Claude Code usage, or audit agent-heavy workflows.
How do I add TokenEyez to my agent?
Configure stdio MCP with npx @tokeneyez/mcp per registry hints, restart your client, and ensure local permissions allow the tracker to read configured sources.