Developer · Local MCP server
Token Meter
Local-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.whdrnr2583-cmd/token-meter- Version
- 0.1.17
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-06-10
- Updated
- 2026-06-10
- Publisher
- whdrnr2583-cmd (GitHub) · 2 servers with pages here
- Website
- token-meter.dev
- Repository
- github.com/whdrnr2583-cmd/token-meter
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @whdrnr2583/token-meter | 0.1.17 | stdio |
How to connect Token Meter
Token Meter runs locally from a Node.js package published to the npm registry: @whdrnr2583/token-meter version 0.1.17. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @whdrnr2583/token-meter@0.1.17.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"token-meter": {
"command": "npx",
"args": [
"-y",
"@whdrnr2583/token-meter@0.1.17"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from whdrnr2583-cmd (GitHub)
| Server | Runs |
|---|---|
| koreanpulseKorean equities in English: DART filings, activist & foreign-holder classification, KRX news. | Remote · HTTP |
More developer servers
| Server | Runs |
|---|---|
| Toggl MCPMCP server for Toggl Track — gives Claude access to your time tracking data. | Local · stdio |
| tokcalc MCP ServerLLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost. | Remote & Local · HTTP, stdio |
| Token CompressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. | Local · stdio |
| Token EnhancerCuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM. | Local · stdio |
| Token PilotSave up to 80% tokens when AI reads code via AST-aware structural reading. | Local · stdio |
| Token SaviorStructural codebase MCP server with persistent memory: navigate by symbol, recall across sessions. | Local · stdio |
| Token ToolDeploy compliant ERC-20 tokens from any AI agent. 17 tools, 10 networks, CertiK-audited. | Local · stdio |
| Tokencost DevLLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM. | Local · stdio |