Tokencost Dev MCP Server

by jeff-atriumn Your server? Claim it

local only

Tokencost Dev runs on your own machine — the client starts it, so there is no endpoint to ping. 148 installs a week from npm. Last commit 22 Sep 2026.

LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM

Installs per day peak 17 · avg 7 · +35% w/w

a month agotoday

148

Installs / week

npm · tokencost-dev

Stars

1 open issue

22 Sep 2026

Last commit

no releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Tokencost Dev every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 tokencost-dev -- npx -y tokencost-dev

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

{
  "mcpServers": {
    "tokencost-dev": {
      "command": "npx",
      "args": [
        "-y",
        "tokencost-dev"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.tokencost-dev]
command = "npx"
args = ["-y", "tokencost-dev"]

.cursor/mcp.json

{
  "mcpServers": {
    "tokencost-dev": {
      "command": "npx",
      "args": [
        "-y",
        "tokencost-dev"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "tokencost-dev": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "tokencost-dev"
      ]
    }
  }
}

Alternatives to Tokencost Dev

same job, measured the same way

Modelpricewatch

by modelpricewatch

Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.

59 installs/wk 4 tools answering

AI Cost Analyzer

by vpatser1

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

37 installs/wk local only

OptimToken

by optimnow

Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.

5 tools answering

LLM Hosting Pricing

by llmhosting

LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history

5 tools answering

AICostBudget AI API Pricing

by aicostbudget

Read-only source-linked AI API prices, comparisons, cost estimates, and price changes.

98 installs/wk local only

Compare Cloud Costs

by comparecloudcosts

Compare cloud and AI model pricing across AWS, Azure, GCP, Oracle, DigitalOcean and more.

47 installs/wk local only

Synap

by linkrra

Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.

4 tools answering

Compute Finance Oracle

by compute-finance

Live AI compute pricing oracle — real-time LLM model prices across providers

401 installs/wk local only

Tokencost Dev — questions

Answers built from our own checks of this server.

Why is there no uptime for Tokencost Dev?

Tokencost Dev 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 tokencost-dev was installed 148 times last week.

How do I connect Tokencost Dev?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls tokencost-dev straight from npm; nothing to host, nothing to sign up for.

How many people use Tokencost Dev?

The npm package tokencost-dev was installed 148 times in the last week. Week over week that is +35%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Tokencost Dev open source?

Yes — it is published under the MIT licence, written in TypeScript, 1 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.