MCP Token Optimizer MCP Server

by rccola990-cloud Your server? Claim it

local only

MCP Token Optimizer runs on your own machine — the client starts it, so there is no endpoint to ping. 25 installs a week from npm.

Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 24 · avg 7 · -14% w/w

a month agotoday

Installs / week

npm · mcp-token-optimizer

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-token-optimizer -- npx -y mcp-token-optimizer

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-token-optimizer": {
      "args": [
        "-y",
        "mcp-token-optimizer"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-token-optimizer]
command = "npx"
args = ["-y", "mcp-token-optimizer"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-token-optimizer": {
      "args": [
        "-y",
        "mcp-token-optimizer"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp-token-optimizer": {
      "args": [
        "-y",
        "mcp-token-optimizer"
      ],
      "command": "npx"
    }
  }
}

Alternatives to MCP Token Optimizer

same job, measured the same way

Modelcostsaver

by sachinuppal

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

58 installs/wk local only

Modelglass

by modelglass

Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.

answering

Green MCP

by rlawogh1005

Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.

71 installs/wk local only

Agentcents

by labham-llc

Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.

242 installs/wk local only

AI Cost Analyzer

by vpatser1

Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

40 installs/wk local only

llmtrim

by fkiene

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

266 installs/wk local only

LLM Cost Estimator

by waqarulwahab

Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.

29 installs/wk local only

Promptbudget MCP

by mukundakatta

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

28 installs/wk local only

MCP Token Optimizer — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP Token Optimizer?

MCP Token Optimizer runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package mcp-token-optimizer was installed 25 times last week.

Is MCP Token Optimizer still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect MCP Token Optimizer?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcp-token-optimizer straight from npm; nothing to host, nothing to sign up for.

How many people use MCP Token Optimizer?

The npm package mcp-token-optimizer was installed 25 times in the last week. Week over week that is -14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.