Developer · Local MCP server

Token Enhancer

Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.xelektron/token-enhancer
Version
0.2.1
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-04-03
Updated
2026-04-03
Publisher
xelektron (GitHub)
Repository
github.com/xelektron/token-enhancer
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIxelektron-token-enhancer0.2.1stdioNone declared

How to connect Token Enhancer

Token Enhancer runs locally from a Python package published to PyPI: xelektron-token-enhancer version 0.2.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx xelektron-token-enhancer.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "token-enhancer": {
      "command": "uvx",
      "args": [
        "xelektron-token-enhancer"
      ]
    }
  }
}

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 developer servers

All 6,250 →
ServerRunsEndpoint or package
TodoxMemory for coding agents: the decisions, the dead ends, and where the last session stopped.Remote · HTTPtodox.dev
Toggl MCPMCP server for Toggl Track — gives Claude access to your time tracking data.Local · stdionpm: @souravpn/toggl-mcp
tokcalc MCP ServerLLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.Remote & Local · HTTP, stdiotokcalc.vercel.app
Token CompressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.Local · stdioPyPI: token-compressor-mcp
Token MeterLocal-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown.Local · stdionpm: @whdrnr2583/token-meter
Token PilotSave up to 80% tokens when AI reads code via AST-aware structural reading.Local · stdionpm: token-pilot
Token SaviorStructural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.Local · stdioPyPI: token-savior-recall
Token ToolDeploy compliant ERC-20 tokens from any AI agent. 17 tools, 10 networks, CertiK-audited.Local · stdionpm: token-tool-mcp