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. 34 installs a week from npm. Last commit 15 Sep 2026.

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

Installs per day peak 14 · avg 6 · -49% w/w

a month agotoday

Installs / week

npm · tokencost-dev

Stars

0 open issues

15 Sep 2026

Last commit

0 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": {
      "args": [
        "-y",
        "tokencost-dev"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

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

.cursor/mcp.json

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

.vscode/mcp.json

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

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.

43 installs/wk 4 tools answering

AI Cost Analyzer

by vpatser1

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

40 installs/wk local only

LLM Hosting Pricing

by llmhosting

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

5 tools answering

Compute Finance Oracle

by compute-finance

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

250 installs/wk local only

OCI Pricing

by jasonwilbur

Oracle Cloud Infrastructure pricing data with cost calculators and comparisons

50 installs/wk local only

Inferenceindexer MCP

by desmartin01

AI inference pricing for agents: live and historical model prices, provider comparison.

388 installs/wk 10 tools answering

OptimToken

by optimnow

Compare LLM API pricing, estimate workload costs, and benchmark cloud compute. By OptimNow.

5 tools answering

Rival

by nuance-dev

Query AI model benchmarks, pricing, and comparisons from rival.tips

23 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 34 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 with the file path 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 34 times in the last week. Week over week that is -49%. 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 and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.